{
  "benchmark_line": "gamebench2",
  "comparability_tuples": [
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "balanced",
      "results_cut_id": "20260925_163935",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_kind": "full_freedom"
    },
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "baseline",
      "results_cut_id": "20260925_163935",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_kind": "full_freedom"
    },
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "intensive",
      "results_cut_id": "20260925_163935",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_kind": "full_freedom"
    },
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "mixed",
      "results_cut_id": "20260925_163935",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_kind": "full_freedom"
    },
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "aggregate",
      "results_cut_id": "20260925_163935",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_kind": "overall"
    }
  ],
  "generated_at": "2026-09-25T16:39:35Z",
  "public_release_id": "gb2-20260925-719069527ef4",
  "results_cut_id": "gb2-20260925-719069527ef4",
  "rows": [
    {
      "admitted_plugins": 8,
      "attempted_matches": 1916,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-6-astra:af89b97f9d676a8c",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 1.47583,
        "mean": 1.30343,
        "median": 1.3074612499999998,
        "min": 1.077205,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-05": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 10.42744
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 94.27795884318934,
      "contributing_entrants": null,
      "distinct_rated_opponents": 180,
      "draws": 63,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:44:38Z",
      "losses": 82,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 80.00375714481252,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1916,
      "rating_method": "sequential_elo",
      "raw_elo": 2135.6057738383734,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 94.27795884318934,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1771
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-fable-5-1:d307977c9774b8cb",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 13
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 11.79121,
        "mean": 5.021086745700856,
        "median": 3.933625,
        "min": 2.3764558334148846,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 3,
          "boardgame-list-prices-2026-09-08": 10
        },
        "run_count": 11,
        "token_priced_attempt_count": 13,
        "total": 48.73911793121369
      },
      "codegen_evaluated_cells": 11,
      "conditional_success_score": 91.38911158312541,
      "contributing_entrants": null,
      "distinct_rated_opponents": 182,
      "draws": 70,
      "eligibility_flag": true,
      "entry_count": 11,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-intensive",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.8181818181818182,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "infra_failures_excluded": 5,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:12:04Z",
      "losses": 146,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 79.87031463289088,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2590,
      "rating_method": "sequential_elo",
      "raw_elo": 2118.3599419593484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.18181818181818182,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 91.38911158312541,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2374
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1962,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-6-astra:9acce95ba71bd7c5",
      "capped_draws": 21,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.48718,
        "mean": 0.4090425,
        "median": 0.40659249999999997,
        "min": 0.311405,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-05": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 3.2723400000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 81.66546467894545,
      "contributing_entrants": null,
      "distinct_rated_opponents": 179,
      "draws": 204,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:19:37Z",
      "losses": 161,
      "max_score": 95.69162884853398,
      "measured_at": null,
      "min_score": 58.93727047228494,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1962,
      "rating_method": "sequential_elo",
      "raw_elo": 1995.377815650245,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 81.66546467894545,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1597
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 720,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5-5:12d35a0c8ebcfc9f",
      "capped_draws": 3,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 3.092384,
        "mean": 1.98688675,
        "median": 1.871197,
        "min": 1.357152,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 11
        },
        "run_count": 9,
        "token_priced_attempt_count": 11,
        "total": 17.677192
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 80.9535676866771,
      "contributing_entrants": null,
      "distinct_rated_opponents": 153,
      "draws": 22,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:15Z",
      "losses": 35,
      "max_score": 90.00227559221021,
      "measured_at": null,
      "min_score": 62.15278254588686,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 720,
      "rating_method": "sequential_elo",
      "raw_elo": 1992.9836002881682,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 80.9535676866771,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 663
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1962,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-6-astra:8883275fa81b106a",
      "capped_draws": 11,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.26443,
        "mean": 0.23918625000000002,
        "median": 0.241805,
        "min": 0.2072175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-05": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.91349
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 76.98193882052338,
      "contributing_entrants": null,
      "distinct_rated_opponents": 180,
      "draws": 285,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:30Z",
      "losses": 211,
      "max_score": 97.38715231698653,
      "measured_at": null,
      "min_score": 50.02617127882385,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1962,
      "rating_method": "sequential_elo",
      "raw_elo": 1961.253142422849,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 76.98193882052338,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1466
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-fable-5-1:2ceef8038de90922",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 1.511677676840267,
        "mean": 1.1541937045345083,
        "median": 1.126127596791556,
        "min": 0.7961115304367101,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 9.233549636276065
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 75.04188072111677,
      "contributing_entrants": null,
      "distinct_rated_opponents": 186,
      "draws": 161,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:05:54Z",
      "losses": 241,
      "max_score": 91.91733247569104,
      "measured_at": null,
      "min_score": 27.6720155573788,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1950,
      "rating_method": "sequential_elo",
      "raw_elo": 1946.0202078820396,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 75.04188072111677,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1548
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-fable-5-1:fdf38228456af115",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.8940315948861309,
        "mean": 0.7923815012907612,
        "median": 0.7948316688813246,
        "min": 0.6566066208996896,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 6.33905201032609
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 74.53643108789285,
      "contributing_entrants": null,
      "distinct_rated_opponents": 183,
      "draws": 217,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:44:45Z",
      "losses": 217,
      "max_score": 88.63477864319661,
      "measured_at": null,
      "min_score": 54.829742723095954,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1918,
      "rating_method": "sequential_elo",
      "raw_elo": 1932.842927550027,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 74.53643108789285,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1484
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 814,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5-5:7dce3bfc0734dff8",
      "capped_draws": 4,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.728964,
        "mean": 0.33381875,
        "median": 0.267474,
        "min": 0.167816,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 3.0063079999999998
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 74.49726125112892,
      "contributing_entrants": null,
      "distinct_rated_opponents": 162,
      "draws": 26,
      "eligibility_flag": true,
      "entry_count": 9,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.8888888888888888,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:45Z",
      "losses": 61,
      "max_score": 81.57822709514194,
      "measured_at": null,
      "min_score": 69.8950709756612,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 814,
      "rating_method": "sequential_elo",
      "raw_elo": 1923.1468343541355,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 74.49726125112892,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 727
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 2366,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 4,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 3,
        "max": 2.09943,
        "mean": 1.379653125,
        "median": 1.3205149999999999,
        "min": 0.8875599999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 22.07445
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 76.79197650973506,
      "contributing_entrants": null,
      "distinct_rated_opponents": 190,
      "draws": 155,
      "eligibility_flag": true,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.8125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:30Z",
      "losses": 326,
      "max_score": 90.34746663281791,
      "measured_at": null,
      "min_score": 59.671054671727674,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 3,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.8125,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2366,
      "rating_method": "sequential_elo",
      "raw_elo": 1947.2184048674094,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 72.90741299156647,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1885
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2618,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 8,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 1.17244375,
        "mean": 0.7965692187500001,
        "median": 0.7419175,
        "min": 0.6308437499999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 6.37255375
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 69.89581987459516,
      "contributing_entrants": null,
      "distinct_rated_opponents": 184,
      "draws": 195,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:11:13Z",
      "losses": 438,
      "max_score": 89.24673663502878,
      "measured_at": null,
      "min_score": 51.53506842461099,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2617,
      "rating_method": "sequential_elo",
      "raw_elo": 1861.492100901898,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 69.89581987459516,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1984
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1990,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-fable-5:9411c67711dccbe8",
      "capped_draws": 119,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 2.14955,
        "mean": 1.47056875,
        "median": 1.411685,
        "min": 0.98262,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 11.76455
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 65.1419679067195,
      "contributing_entrants": null,
      "distinct_rated_opponents": 180,
      "draws": 309,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:12Z",
      "losses": 454,
      "max_score": 85.53702993381843,
      "measured_at": null,
      "min_score": 35.23351331310822,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1983,
      "rating_method": "sequential_elo",
      "raw_elo": 1775.952167016037,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 65.1419679067195,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1220
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 692,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-6-sol:410ceff1171c2cf1",
      "capped_draws": 3,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.225321,
        "mean": 0.20679475000000003,
        "median": 0.2051385,
        "min": 0.185721,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.6543580000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 61.55693513846125,
      "contributing_entrants": null,
      "distinct_rated_opponents": 146,
      "draws": 64,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:29:41Z",
      "losses": 121,
      "max_score": 82.55615873333252,
      "measured_at": null,
      "min_score": 11.206070516617746,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 692,
      "rating_method": "sequential_elo",
      "raw_elo": 1784.6419125091616,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 61.55693513846125,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 507
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 2382,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 61,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 2.2530275,
        "mean": 1.51903,
        "median": 1.4938600000000002,
        "min": 1.088255,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 12.15224
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 63.56633841927054,
      "contributing_entrants": null,
      "distinct_rated_opponents": 181,
      "draws": 374,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:53:32Z",
      "losses": 480,
      "max_score": 90.9620272870252,
      "measured_at": null,
      "min_score": 26.396024096701737,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2375,
      "rating_method": "sequential_elo",
      "raw_elo": 1811.0896026439925,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 61.479341753727496,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1521
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2100,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3:2dbca3140c06e14c",
      "capped_draws": 137,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.23469315999999998,
        "mean": 0.156944395,
        "median": 0.1664265,
        "min": 0.07192,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 1.25555516
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 60.37629544290532,
      "contributing_entrants": null,
      "distinct_rated_opponents": 183,
      "draws": 377,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:30Z",
      "losses": 497,
      "max_score": 91.34449020371359,
      "measured_at": null,
      "min_score": 23.547509730974397,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2098,
      "rating_method": "sequential_elo",
      "raw_elo": 1763.5848588349686,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 60.37629544290532,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1224
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 820,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5-5:e7d2796533ceda7c",
      "capped_draws": 7,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.124844,
        "mean": 0.11677924999999999,
        "median": 0.118817,
        "min": 0.094852,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 1.052792
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 59.7581605831015,
      "contributing_entrants": null,
      "distinct_rated_opponents": 167,
      "draws": 128,
      "eligibility_flag": true,
      "entry_count": 9,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 9,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:34:12Z",
      "losses": 156,
      "max_score": 79.85364697365718,
      "measured_at": null,
      "min_score": 34.34311959065729,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 820,
      "rating_method": "sequential_elo",
      "raw_elo": 1775.8111490247318,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 59.7581605831015,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 536
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 2916,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 41,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.551725,
        "mean": 0.44617968750000003,
        "median": 0.45788,
        "min": 0.33828,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 7.138875
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 61.757649808905576,
      "contributing_entrants": null,
      "distinct_rated_opponents": 195,
      "draws": 387,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:14:25Z",
      "losses": 485,
      "max_score": 82.13477554310234,
      "measured_at": null,
      "min_score": 15.978871709726342,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2914,
      "rating_method": "sequential_elo",
      "raw_elo": 1820.5481727667586,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 59.73003562775136,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 2042
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1478,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 25,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 1.38945,
        "mean": 0.93123625,
        "median": 0.95991,
        "min": 0.36561,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 7.44989
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 60.64361772447914,
      "contributing_entrants": null,
      "distinct_rated_opponents": 178,
      "draws": 203,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:11:59Z",
      "losses": 305,
      "max_score": 78.12478117978807,
      "measured_at": null,
      "min_score": 34.48092158803702,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1478,
      "rating_method": "sequential_elo",
      "raw_elo": 1766.38446726309,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 58.652579210624985,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 970
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 3124,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 224,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.5221625,
        "mean": 0.2856328125,
        "median": 0.2536225,
        "min": 0.2178175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 4.570125000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 59.77980290368503,
      "contributing_entrants": null,
      "distinct_rated_opponents": 193,
      "draws": 630,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:04:48Z",
      "losses": 544,
      "max_score": 88.30380211671529,
      "measured_at": null,
      "min_score": 30.879083926934985,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3121,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.8890072464121,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 57.81712497651046,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1947
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1938,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-6:bca3abc3bf41095f",
      "capped_draws": 70,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.179588,
        "mean": 0.12726625,
        "median": 0.12371399999999999,
        "min": 0.092184,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 1.01813
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 57.76474815367045,
      "contributing_entrants": null,
      "distinct_rated_opponents": 186,
      "draws": 411,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:25:05Z",
      "losses": 451,
      "max_score": 78.05231532268954,
      "measured_at": null,
      "min_score": 24.805218937462044,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1932,
      "rating_method": "sequential_elo",
      "raw_elo": 1751.035141388364,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 57.76474815367045,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1070
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 720,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-6-sol:a64b94562f86a4f3",
      "capped_draws": 18,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.1118895,
        "mean": 0.07831456249999999,
        "median": 0.0772785,
        "min": 0.0550535,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.6265165
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 57.34076897878964,
      "contributing_entrants": null,
      "distinct_rated_opponents": 144,
      "draws": 124,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:29:47Z",
      "losses": 144,
      "max_score": 78.85328563520711,
      "measured_at": null,
      "min_score": 31.714134573439228,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 720,
      "rating_method": "sequential_elo",
      "raw_elo": 1745.257481737596,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 57.34076897878964,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 452
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 6637,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 186,
      "codegen_cost_usd": {
        "admitted_cell_count": 25,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 31
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 31,
        "run_count": 28,
        "total": 0.0
      },
      "codegen_evaluated_cells": 25,
      "conditional_success_score": 56.87873766350323,
      "contributing_entrants": null,
      "distinct_rated_opponents": 198,
      "draws": 889,
      "eligibility_flag": true,
      "entry_count": 25,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 22,
      "first_pass_rate": 0.88,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "infra_failures_excluded": 5,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:04:41Z",
      "losses": 1969,
      "max_score": 67.13193639618068,
      "measured_at": null,
      "min_score": 49.54900667277811,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6449,
      "rating_method": "sequential_elo",
      "raw_elo": 1693.7247943349419,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 3,
      "repaired_rate": 0.12,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 56.87873766350323,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 182,
      "wins": 3591
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2638,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 139,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.24740375,
        "mean": 0.229063125,
        "median": 0.23243875,
        "min": 0.20046375,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.832505
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 56.590178181129204,
      "contributing_entrants": null,
      "distinct_rated_opponents": 180,
      "draws": 422,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:44Z",
      "losses": 729,
      "max_score": 74.92326063693565,
      "measured_at": null,
      "min_score": 36.36805948391099,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2636,
      "rating_method": "sequential_elo",
      "raw_elo": 1684.8387853717302,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 56.590178181129204,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1485
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2048,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:b4ca94f8b60a9e88",
      "capped_draws": 108,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 10
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.7896974949512139,
        "mean": 0.4317783571024416,
        "median": 0.3306270924500423,
        "min": 0.277380977244658,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 3.4542268568195333
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 55.185255291851604,
      "contributing_entrants": null,
      "distinct_rated_opponents": 185,
      "draws": 528,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:09Z",
      "losses": 499,
      "max_score": 81.83360524090116,
      "measured_at": null,
      "min_score": 19.044287744530894,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2042,
      "rating_method": "sequential_elo",
      "raw_elo": 1727.2085997821755,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 55.185255291851604,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1015
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1397,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 126,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 4.4173,
        "mean": 2.7356843750000004,
        "median": 2.536595,
        "min": 2.045485,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.885475
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 56.835196114717284,
      "contributing_entrants": null,
      "distinct_rated_opponents": 171,
      "draws": 306,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:14Z",
      "losses": 248,
      "max_score": 85.64043148326957,
      "measured_at": null,
      "min_score": 10.026592849743277,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1396,
      "rating_method": "sequential_elo",
      "raw_elo": 1749.6293859235354,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 54.969194898876594,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 842
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2120,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3-flash:6bc93e3f26e0f0e5",
      "capped_draws": 204,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.01518705,
        "mean": 0.00578608125,
        "median": 0.0045066875,
        "min": 0.0032555,
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.04628865
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 54.61401951813503,
      "contributing_entrants": null,
      "distinct_rated_opponents": 183,
      "draws": 527,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:42:02Z",
      "losses": 647,
      "max_score": 73.9709651519967,
      "measured_at": null,
      "min_score": 19.58473584796164,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2113,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.7927997705892,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 54.61401951813503,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 939
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1966,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-fable-5:1f4ca1763387a608",
      "capped_draws": 27,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.73774,
        "mean": 0.5233875,
        "median": 0.47084000000000004,
        "min": 0.34112,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.1871
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.2483566362053,
      "contributing_entrants": null,
      "distinct_rated_opponents": 189,
      "draws": 383,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:33Z",
      "losses": 546,
      "max_score": 83.86890130218805,
      "measured_at": null,
      "min_score": 13.925660427832574,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1966,
      "rating_method": "sequential_elo",
      "raw_elo": 1702.2162215820367,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 53.2483566362053,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1037
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 670,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:b85a8fb56d024434",
      "capped_draws": 49,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.031583268,
        "mean": 0.02640173625,
        "median": 0.026524292999999997,
        "min": 0.018252918,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.21121389
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.001670581745614,
      "contributing_entrants": null,
      "distinct_rated_opponents": 157,
      "draws": 143,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:24:55Z",
      "losses": 119,
      "max_score": 75.19336305189155,
      "measured_at": null,
      "min_score": 26.984183127320136,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 670,
      "rating_method": "sequential_elo",
      "raw_elo": 1693.9878380220237,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 53.001670581745614,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 408
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2218,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-6:d94ddefd8b9f53eb",
      "capped_draws": 296,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.28029,
        "mean": 0.23409475,
        "median": 0.240558,
        "min": 0.184404,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 1.8727580000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.89362205123531,
      "contributing_entrants": null,
      "distinct_rated_opponents": 187,
      "draws": 572,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:19:35Z",
      "losses": 614,
      "max_score": 80.29583807622168,
      "measured_at": null,
      "min_score": 32.37146553254912,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2217,
      "rating_method": "sequential_elo",
      "raw_elo": 1663.399470048735,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 52.89362205123531,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1031
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 4581,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 556,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.531673125,
        "mean": 0.47737264687500003,
        "median": 0.48302475,
        "min": 0.3855675,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 7.6379623500000005
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 56.14065082660016,
      "contributing_entrants": null,
      "distinct_rated_opponents": 195,
      "draws": 843,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-07"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:41:54Z",
      "losses": 1263,
      "max_score": 84.32762532825016,
      "measured_at": null,
      "min_score": 37.63782150579934,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4575,
      "rating_method": "sequential_elo",
      "raw_elo": 1694.8142290263713,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 52.24476245238841,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 2469
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2174,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy4-preview:2077a0aa15ce66b2",
      "capped_draws": 376,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.151385561,
        "mean": 0.12117269062500001,
        "median": 0.1216224665,
        "min": 0.099918984,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.9693815250000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.067151128510105,
      "contributing_entrants": null,
      "distinct_rated_opponents": 185,
      "draws": 606,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:33:41Z",
      "losses": 595,
      "max_score": 77.83883887689821,
      "measured_at": null,
      "min_score": 24.654353233120247,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": 1.0,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2168,
      "rating_method": "sequential_elo",
      "raw_elo": 1648.4158119703436,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 52.067151128510105,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 967
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2092,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-8-flash:e50b23a03b02a00c",
      "capped_draws": 164,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.2764612177973556,
        "mean": 0.14318721034763582,
        "median": 0.1303062996496891,
        "min": 0.10133749410144509,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 1.1454976827810865
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 51.44019386589474,
      "contributing_entrants": null,
      "distinct_rated_opponents": 179,
      "draws": 341,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:44Z",
      "losses": 655,
      "max_score": 83.10880420461697,
      "measured_at": null,
      "min_score": 21.023257576979688,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2090,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.6772984597571,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 51.44019386589474,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1094
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2198,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash:188028ef432c73f8",
      "capped_draws": 115,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.5094276945411561,
        "mean": 0.27056867355814085,
        "median": 0.2333324037943521,
        "min": 0.1875185140307643,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 2.164549388465127
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 51.327641268902916,
      "contributing_entrants": null,
      "distinct_rated_opponents": 179,
      "draws": 471,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:53:18Z",
      "losses": 694,
      "max_score": 85.75732154194154,
      "measured_at": null,
      "min_score": 15.041311096948304,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2198,
      "rating_method": "sequential_elo",
      "raw_elo": 1672.51049243344,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 51.327641268902916,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1033
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3182,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 106,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.13495079999999998,
        "mean": 0.07455065,
        "median": 0.0607138,
        "min": 0.0448404,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.5964052
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 51.011009449206256,
      "contributing_entrants": null,
      "distinct_rated_opponents": 180,
      "draws": 589,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:16:11Z",
      "losses": 885,
      "max_score": 79.71896425856343,
      "measured_at": null,
      "min_score": 22.083742425713893,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3181,
      "rating_method": "sequential_elo",
      "raw_elo": 1658.1800255201888,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 51.011009449206256,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1707
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2060,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3-flash:1540ade2fda6b881",
      "capped_draws": 205,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.02871725,
        "mean": 0.014901165624999999,
        "median": 0.013297725,
        "min": 0.0073485,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.11920932499999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.8933219700669,
      "contributing_entrants": null,
      "distinct_rated_opponents": 179,
      "draws": 434,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:41:47Z",
      "losses": 648,
      "max_score": 73.82177341477453,
      "measured_at": null,
      "min_score": 20.64380726893646,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2060,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.9388407447273,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 50.8933219700669,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 978
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2106,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-3:111be2eb4c7d6522",
      "capped_draws": 18,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.07423675,
        "mean": 0.05217515625,
        "median": 0.050446875,
        "min": 0.04135875,
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.41740125000000006
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.63974829395818,
      "contributing_entrants": null,
      "distinct_rated_opponents": 185,
      "draws": 321,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:27:19Z",
      "losses": 680,
      "max_score": 78.27779768942712,
      "measured_at": null,
      "min_score": 26.121442848759003,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2098,
      "rating_method": "sequential_elo",
      "raw_elo": 1654.5132916237949,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 50.63974829395818,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1097
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 724,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3-flashx:43f4326da261c154",
      "capped_draws": 59,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.09557687,
        "mean": 0.060370179999999996,
        "median": 0.057823150000000004,
        "min": 0.03447845,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.48296143999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.42811883048915,
      "contributing_entrants": null,
      "distinct_rated_opponents": 153,
      "draws": 148,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:21:57Z",
      "losses": 197,
      "max_score": 71.74427757233467,
      "measured_at": null,
      "min_score": 24.546741166561926,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 723,
      "rating_method": "sequential_elo",
      "raw_elo": 1641.3311149504323,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 50.42811883048915,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 378
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1808,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 17,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.0878628,
        "mean": 0.0635932,
        "median": 0.06199639999999999,
        "min": 0.0498884,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.5087456
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 48.89069299775914,
      "contributing_entrants": null,
      "distinct_rated_opponents": 173,
      "draws": 425,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:30Z",
      "losses": 501,
      "max_score": 71.98011275701009,
      "measured_at": null,
      "min_score": 18.426880670928522,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1806,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.9963976842268,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 48.89069299775914,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 880
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1740,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-27b:739c4d774075dc83",
      "capped_draws": 126,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.3521656,
        "mean": 0.19569013062499999,
        "median": 0.187188825,
        "min": 0.119031025,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 1.5655210449999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.3101665311099,
      "contributing_entrants": null,
      "distinct_rated_opponents": 182,
      "draws": 216,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:56:38Z",
      "losses": 620,
      "max_score": 74.90167026913919,
      "measured_at": null,
      "min_score": 32.556710798345804,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": 0.75,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1740,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.0401794830425,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 48.68009515429089,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 904
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1920,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy4-preview:014a9ceb67d5b786",
      "capped_draws": 19,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.190258393,
        "mean": 0.135826968,
        "median": 0.126875313,
        "min": 0.097439089,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 1.086615744
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 49.77163099580157,
      "contributing_entrants": null,
      "distinct_rated_opponents": 191,
      "draws": 310,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:11:51Z",
      "losses": 648,
      "max_score": 81.28231996103942,
      "measured_at": null,
      "min_score": 9.957083818816807,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": 0.875,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1919,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.2716358517375,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 48.13753926565109,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 961
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2208,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-flash:98dfb2fac355b676",
      "capped_draws": 348,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.061982706,
        "mean": 0.0376887,
        "median": 0.037827133,
        "min": 0.02582591,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.3015096
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.30415802742198,
      "contributing_entrants": null,
      "distinct_rated_opponents": 188,
      "draws": 742,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:29:21Z",
      "losses": 579,
      "max_score": 74.00144873524822,
      "measured_at": null,
      "min_score": 24.898458456294655,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2207,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.6798664080998,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 47.30415802742198,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 886
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 688,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:3fe477f1e3ed7e39",
      "capped_draws": 66,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.02304638,
        "mean": 0.0178225775,
        "median": 0.01816367,
        "min": 0.01029504,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 11
        },
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.14258062000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.115778688864275,
      "contributing_entrants": null,
      "distinct_rated_opponents": 158,
      "draws": 126,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:54Z",
      "losses": 212,
      "max_score": 73.64786897600108,
      "measured_at": null,
      "min_score": 20.29762262352045,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": 1.0,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 688,
      "rating_method": "sequential_elo",
      "raw_elo": 1605.2982547213696,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 47.115778688864275,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 350
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2162,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-8-flash:6b8b02f1f727feff",
      "capped_draws": 221,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.12249677080183623,
        "mean": 0.07182689102312519,
        "median": 0.06440174762499168,
        "min": 0.044067488277453076,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.5746151281850016
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.04816057368627,
      "contributing_entrants": null,
      "distinct_rated_opponents": 186,
      "draws": 650,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:52:47Z",
      "losses": 647,
      "max_score": 71.62237123829571,
      "measured_at": null,
      "min_score": 15.032375698995798,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2155,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.8947278491648,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 47.04816057368627,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 858
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2090,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-fable-5:346aadd5d76b812b",
      "capped_draws": 61,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.35085,
        "mean": 0.28860625,
        "median": 0.282885,
        "min": 0.22654,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 2.30885
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.59349239407559,
      "contributing_entrants": null,
      "distinct_rated_opponents": 187,
      "draws": 527,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:59:44Z",
      "losses": 627,
      "max_score": 70.75317794233399,
      "measured_at": null,
      "min_score": 8.30135369548809,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2088,
      "rating_method": "sequential_elo",
      "raw_elo": 1642.0653756966155,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 46.59349239407559,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 934
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 720,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-6-sol:a790476a054b6a1d",
      "capped_draws": 6,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.052136,
        "mean": 0.043196000000000005,
        "median": 0.04354475,
        "min": 0.033231000000000004,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.34556800000000004
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.49429384120996,
      "contributing_entrants": null,
      "distinct_rated_opponents": 149,
      "draws": 133,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:24:43Z",
      "losses": 214,
      "max_score": 67.0440325823212,
      "measured_at": null,
      "min_score": 11.969256362592526,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 720,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.3676025098832,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 46.49429384120996,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 373
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2094,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash:79befaaad7974375",
      "capped_draws": 146,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 10
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.27117240812024124,
        "mean": 0.1983136265434789,
        "median": 0.18868274576048882,
        "min": 0.15676593388665558,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 1.5865090123478314
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 45.94264480977134,
      "contributing_entrants": null,
      "distinct_rated_opponents": 179,
      "draws": 567,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:25:05Z",
      "losses": 693,
      "max_score": 70.75278873396961,
      "measured_at": null,
      "min_score": 12.815210820746566,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2093,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.139740546044,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 45.94264480977134,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 833
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2708,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 53,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.50466,
        "mean": 0.35099375,
        "median": 0.321349,
        "min": 0.220732,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 2.80795
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.793190429889094,
      "contributing_entrants": null,
      "distinct_rated_opponents": 182,
      "draws": 619,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:11:51Z",
      "losses": 925,
      "max_score": 64.64982345476963,
      "measured_at": null,
      "min_score": 13.894809860305726,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2707,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.327780290315,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 44.793190429889094,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1163
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2802,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 278,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.4120425,
        "mean": 0.283374375,
        "median": 0.26543625,
        "min": 0.2124125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 2.266995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.08690114479181,
      "contributing_entrants": null,
      "distinct_rated_opponents": 181,
      "draws": 900,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:05:53Z",
      "losses": 780,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2796,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.5353596497243,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 44.08690114479181,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1116
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 4953,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 334,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 44
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.3888165,
        "mean": 0.26060548125,
        "median": 0.24728879999999998,
        "min": 0.17802225,
        "recorded_attempt_count": 44,
        "run_count": 16,
        "total": 4.1696877
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 45.26783194625648,
      "contributing_entrants": null,
      "distinct_rated_opponents": 198,
      "draws": 1154,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-08"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:33:39Z",
      "losses": 1421,
      "max_score": 77.04707674780836,
      "measured_at": null,
      "min_score": 7.58639288876681,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4951,
      "rating_method": "sequential_elo",
      "raw_elo": 1619.710091683987,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 43.7816080001001,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 2376
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 696,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-6-luna:06fb6314cedafbae",
      "capped_draws": 4,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.014153675,
        "mean": 0.0117399875,
        "median": 0.011861425,
        "min": 0.0087063,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.0939199
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.62895753236266,
      "contributing_entrants": null,
      "distinct_rated_opponents": 147,
      "draws": 98,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:24:49Z",
      "losses": 261,
      "max_score": 76.68636345470857,
      "measured_at": null,
      "min_score": 27.32497239731715,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 696,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.8301081815516,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 43.62895753236266,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 337
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3506,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 300,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.1077678,
        "mean": 0.076003275,
        "median": 0.070269,
        "min": 0.0550338,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.6080262
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.71441221564036,
      "contributing_entrants": null,
      "distinct_rated_opponents": 189,
      "draws": 942,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:55:04Z",
      "losses": 1150,
      "max_score": 88.12366220504157,
      "measured_at": null,
      "min_score": 16.87963566446718,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 1.0,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3506,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.1727110036659,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 42.71441221564036,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1414
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3096,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 51,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.15394249999999998,
        "mean": 0.12786562499999998,
        "median": 0.13029000000000002,
        "min": 0.10071375,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.022925
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.26651060228551,
      "contributing_entrants": null,
      "distinct_rated_opponents": 188,
      "draws": 710,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:36:49Z",
      "losses": 1005,
      "max_score": 67.54145227969542,
      "measured_at": null,
      "min_score": 9.182072363962202,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3095,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.5380177712655,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 42.26651060228551,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1380
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2200,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-terra:bd3aacb7be18fc49",
      "capped_draws": 165,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.45800250000000003,
        "mean": 0.38340421874999997,
        "median": 0.38428625,
        "min": 0.302056875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 3.0672337499999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.857588040641794,
      "contributing_entrants": null,
      "distinct_rated_opponents": 182,
      "draws": 592,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:32Z",
      "losses": 737,
      "max_score": 76.93585154551911,
      "measured_at": null,
      "min_score": 14.953275323875648,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2194,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.7164673310501,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 41.857588040641794,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 865
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2746,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 269,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.0377622,
        "mean": 0.030833324999999998,
        "median": 0.031411375,
        "min": 0.0247604,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.2466666
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.84697249364046,
      "contributing_entrants": null,
      "distinct_rated_opponents": 182,
      "draws": 914,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:14:16Z",
      "losses": 760,
      "max_score": 81.2042772769244,
      "measured_at": null,
      "min_score": 11.007260933312008,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2742,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.3676871994946,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 41.84697249364046,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1068
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2202,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-8-flash:83795e08736dcbd6",
      "capped_draws": 176,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.041197616649628,
        "mean": 0.031941679879238995,
        "median": 0.03128326283110872,
        "min": 0.026892580852245062,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.25553343903391196
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.5414993237416,
      "contributing_entrants": null,
      "distinct_rated_opponents": 190,
      "draws": 567,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:09:49Z",
      "losses": 743,
      "max_score": 68.57629933967782,
      "measured_at": null,
      "min_score": 7.419192145713985,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2201,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.735873075744,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 41.5414993237416,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 891
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2198,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d0b5b92265541548",
      "capped_draws": 197,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.28337826924,
        "mean": 0.14657020603499998,
        "median": 0.140081106,
        "min": 0.07036986,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 1.1725616482799999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.51017966504621,
      "contributing_entrants": null,
      "distinct_rated_opponents": 184,
      "draws": 627,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:12Z",
      "losses": 658,
      "max_score": 71.8729308953561,
      "measured_at": null,
      "min_score": 9.851281775273819,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2198,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.6032297857455,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 41.51017966504621,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 913
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2236,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro:c37d073d6b142a09",
      "capped_draws": 31,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.06923239834,
        "mean": 0.046577516286750005,
        "median": 0.0458058365,
        "min": 0.023862969,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.37262013029400004
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.259109027909574,
      "contributing_entrants": null,
      "distinct_rated_opponents": 181,
      "draws": 471,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:36Z",
      "losses": 803,
      "max_score": 72.3322501482903,
      "measured_at": null,
      "min_score": 9.212833783417654,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2236,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.7045340306577,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 41.259109027909574,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 962
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 672,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:d1c3d52890a12a42",
      "capped_draws": 85,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.0294003,
        "mean": 0.0190911675,
        "median": 0.019388559,
        "min": 0.011042118,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.15272934000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.942459007178655,
      "contributing_entrants": null,
      "distinct_rated_opponents": 161,
      "draws": 201,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:54Z",
      "losses": 192,
      "max_score": 71.98934050814864,
      "measured_at": null,
      "min_score": 12.331930401575923,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 672,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.501691629872,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 40.942459007178655,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 279
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 2531,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 97,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.060198249999999995,
        "mean": 0.047021,
        "median": 0.04824225,
        "min": 0.0324825,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.376168
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.15120052283497,
      "contributing_entrants": null,
      "distinct_rated_opponents": 189,
      "draws": 621,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:53:18Z",
      "losses": 789,
      "max_score": 72.07963331402082,
      "measured_at": null,
      "min_score": 13.581319779736006,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": 0.875,
      "provider": "Other",
      "provider_key": "other",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2530,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.643988348296,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 40.767301164662655,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1120
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2266,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 262,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.40721066666666667,
        "mean": 0.3468699583333334,
        "median": 0.3476285,
        "min": 0.237408,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 13,
        "total": 4.659586
      },
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 42.5420873263483,
      "contributing_entrants": null,
      "distinct_rated_opponents": 183,
      "draws": 620,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.8,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-08"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:17:03Z",
      "losses": 784,
      "max_score": 68.53774121733082,
      "measured_at": null,
      "min_score": 21.383109438871713,
      "model_code_failure_rate": 0.2,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": 0.8,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2266,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.5189111652264,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 40.233822118374256,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 862
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2052,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:4571486d5f3c5826",
      "capped_draws": 335,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.23894740000000003,
        "mean": 0.121926546075,
        "median": 0.109979,
        "min": 0.0289264146,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.9754123686
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.9162853255109,
      "contributing_entrants": null,
      "distinct_rated_opponents": 187,
      "draws": 706,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:05:48Z",
      "losses": 657,
      "max_score": 76.36982205482883,
      "measured_at": null,
      "min_score": 12.731041209161488,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2052,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.3296590896737,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 39.9162853255109,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 689
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1636,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 198,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.2996388,
        "mean": 0.13471628689999998,
        "median": 0.1144847257,
        "min": 0.027613287599999998,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 1.0777302951999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.12357564467532,
      "contributing_entrants": null,
      "distinct_rated_opponents": 179,
      "draws": 322,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:28:48Z",
      "losses": 644,
      "max_score": 68.29746038794151,
      "measured_at": null,
      "min_score": 19.252817076331517,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": 0.75,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1636,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.37788294831,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 39.200404177689705,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 670
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2272,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 172,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.25803,
        "mean": 0.104435,
        "median": 0.081263,
        "min": 0.075542,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.83548
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.04266865722575,
      "contributing_entrants": null,
      "distinct_rated_opponents": 183,
      "draws": 695,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:44Z",
      "losses": 823,
      "max_score": 62.54041731185943,
      "measured_at": null,
      "min_score": 11.88308300278399,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2271,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.9949595759922,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 39.04266865722575,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 753
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3328,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 173,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.244315,
        "mean": 0.178065,
        "median": 0.19681749999999998,
        "min": 0.10277,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.4245200000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.90241887186665,
      "contributing_entrants": null,
      "distinct_rated_opponents": 188,
      "draws": 807,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:03:41Z",
      "losses": 1195,
      "max_score": 66.84543135872292,
      "measured_at": null,
      "min_score": 9.818228255319736,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3324,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.8860705237812,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.90241887186665,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1322
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2230,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3:9e30a36ab00bd740",
      "capped_draws": 208,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.1610404,
        "mean": 0.053977109999999995,
        "median": 0.0318207,
        "min": 0.0217974,
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.43181688
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.754746612238606,
      "contributing_entrants": null,
      "distinct_rated_opponents": 185,
      "draws": 741,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:01Z",
      "losses": 767,
      "max_score": 67.95978288951696,
      "measured_at": null,
      "min_score": 15.003603712634062,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2227,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.9869711196268,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.754746612238606,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 719
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1734,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 258,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.58673,
        "mean": 0.44285687500000004,
        "median": 0.4176025,
        "min": 0.34269,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.5428550000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.67245608046029,
      "contributing_entrants": null,
      "distinct_rated_opponents": 176,
      "draws": 608,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:20:10Z",
      "losses": 494,
      "max_score": 72.713931668433,
      "measured_at": null,
      "min_score": 17.509396641546054,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1734,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.6062877027753,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.67245608046029,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 632
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2184,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:f9ec308f9bb8850b",
      "capped_draws": 118,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.2163622471450082,
        "mean": 0.1497312219916341,
        "median": 0.14598267318350014,
        "min": 0.09347384547152984,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 1.1978497759330726
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.579637006781816,
      "contributing_entrants": null,
      "distinct_rated_opponents": 193,
      "draws": 604,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:34:02Z",
      "losses": 770,
      "max_score": 60.087876316969584,
      "measured_at": null,
      "min_score": 19.63268358764324,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2183,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.7466459683415,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.579637006781816,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 809
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2188,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro:42034002bcfc5f74",
      "capped_draws": 220,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.176790095,
        "mean": 0.114196574281125,
        "median": 0.09418628700000001,
        "min": 0.06074422244,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.9135725942490001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.51200716437151,
      "contributing_entrants": null,
      "distinct_rated_opponents": 180,
      "draws": 709,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:27:12Z",
      "losses": 770,
      "max_score": 75.28091626993594,
      "measured_at": null,
      "min_score": 10.705367299529621,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2188,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.8265029154468,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.51200716437151,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 709
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1621,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 172,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.45464499999999997,
        "mean": 0.28201406249999994,
        "median": 0.2695775,
        "min": 0.17401125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 2.2561124999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.34190463573641,
      "contributing_entrants": null,
      "distinct_rated_opponents": 186,
      "draws": 538,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:18Z",
      "losses": 521,
      "max_score": 70.82103497731079,
      "measured_at": null,
      "min_score": 10.851384971598858,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1620,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.5799551511332,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.34190463573641,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 561
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1776,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 218,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.34174499999999997,
        "mean": 0.217940625,
        "median": 0.19638,
        "min": 0.14813,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.743525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.05563536159708,
      "contributing_entrants": null,
      "distinct_rated_opponents": 172,
      "draws": 668,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:52:48Z",
      "losses": 492,
      "max_score": 75.74725395578018,
      "measured_at": null,
      "min_score": 11.23707888740107,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1776,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.2826219719254,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.05563536159708,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 616
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3386,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 443,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.4398702,
        "mean": 0.29041619999999996,
        "median": 0.301782,
        "min": 0.095232,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 16
        },
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 2.3233295999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.00861893086849,
      "contributing_entrants": null,
      "distinct_rated_opponents": 183,
      "draws": 1162,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:08:02Z",
      "losses": 1162,
      "max_score": 61.60666625896725,
      "measured_at": null,
      "min_score": 12.829263374876211,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 1.0,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3376,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.6442603943458,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.00861893086849,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1052
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 600,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-7:7805d7703d63f406",
      "capped_draws": 27,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.143752,
        "mean": 0.082967,
        "median": 0.0730072,
        "min": 0.0533856,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 10
        },
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.663736
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.01861015130885,
      "contributing_entrants": null,
      "distinct_rated_opponents": 142,
      "draws": 118,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:34:01Z",
      "losses": 243,
      "max_score": 71.24448433375413,
      "measured_at": null,
      "min_score": 15.846953534414173,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": 0.875,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 600,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.082586073285,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 37.737559341951254,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 239
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2266,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-terra:ac05ef4b9a51340d",
      "capped_draws": 96,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.146648125,
        "mean": 0.09696234375000001,
        "median": 0.09060875000000002,
        "min": 0.083821875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.7756987500000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.3173433619514,
      "contributing_entrants": null,
      "distinct_rated_opponents": 185,
      "draws": 620,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:06Z",
      "losses": 866,
      "max_score": 62.7636226124865,
      "measured_at": null,
      "min_score": 13.179346281696866,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2266,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.6830664292281,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 37.3173433619514,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 780
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1751,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 118,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.325659,
        "mean": 0.25189603125,
        "median": 0.25775625,
        "min": 0.169101,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 2.01516825
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.21858849121705,
      "contributing_entrants": null,
      "distinct_rated_opponents": 177,
      "draws": 528,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:14:25Z",
      "losses": 565,
      "max_score": 60.753181324378254,
      "measured_at": null,
      "min_score": 9.242992989536942,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1749,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.7117053387162,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 37.21858849121705,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 656
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3274,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 261,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.0992248,
        "mean": 0.07433795,
        "median": 0.0774068,
        "min": 0.0424244,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.5947036
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.08056429204913,
      "contributing_entrants": null,
      "distinct_rated_opponents": 188,
      "draws": 969,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:51:32Z",
      "losses": 1152,
      "max_score": 67.15463779430945,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3274,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.2248047238807,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 37.08056429204913,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1153
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1730,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 167,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.144235,
        "mean": 0.12174125,
        "median": 0.121475,
        "min": 0.09594,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.97393
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.88094431118054,
      "contributing_entrants": null,
      "distinct_rated_opponents": 173,
      "draws": 550,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:46Z",
      "losses": 583,
      "max_score": 65.59804006842714,
      "measured_at": null,
      "min_score": 13.849919257531704,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1730,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.4999610577722,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 36.88094431118054,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 597
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": 7127,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 470,
      "codegen_cost_usd": {
        "admitted_cell_count": 26,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 39,
        "run_count": 30,
        "total": 0.0
      },
      "codegen_evaluated_cells": 30,
      "conditional_success_score": 37.91520962417879,
      "contributing_entrants": null,
      "distinct_rated_opponents": 199,
      "draws": 1717,
      "eligibility_flag": true,
      "entry_count": 26,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-06"
      ],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.7,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:23Z",
      "losses": 2719,
      "max_score": 54.925489222319115,
      "measured_at": null,
      "min_score": 15.804848105037715,
      "model_code_failure_rate": 0.13333333333333333,
      "model_code_failures": 4,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": 0.8666666666666667,
      "provider": "Other",
      "provider_key": "other",
      "rank": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 7112,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.997412814324,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 5,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 36.582761420788586,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 2676
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 690,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3-flashx:d5d0648c410f1ae2",
      "capped_draws": 39,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.039202100000000004,
        "mean": 0.026445697500000004,
        "median": 0.025158225,
        "min": 0.015228470000000001,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 11
        },
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.21156558
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.5572086512823,
      "contributing_entrants": null,
      "distinct_rated_opponents": 158,
      "draws": 175,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:09Z",
      "losses": 267,
      "max_score": 63.73802956993577,
      "measured_at": null,
      "min_score": 7.080049745365206,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 690,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.995916003377,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 36.5572086512823,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 248
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2116,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 240,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.173358,
        "mean": 0.1197105,
        "median": 0.119348,
        "min": 0.066054,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.957684
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.2882702960712,
      "contributing_entrants": null,
      "distinct_rated_opponents": 182,
      "draws": 740,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:32Z",
      "losses": 691,
      "max_score": 90.1443955387162,
      "measured_at": null,
      "min_score": 12.573076409935867,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2116,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.850176044393,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 36.2882702960712,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 685
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2324,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d3192451477fbf98",
      "capped_draws": 322,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.18085216,
        "mean": 0.12355654023,
        "median": 0.14129957716,
        "min": 0.04648314,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.98845232184
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.03872592479018,
      "contributing_entrants": null,
      "distinct_rated_opponents": 187,
      "draws": 657,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:05:54Z",
      "losses": 880,
      "max_score": 71.79125135121897,
      "measured_at": null,
      "min_score": 8.629972723433358,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2318,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.539778845137,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 36.03872592479018,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 781
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 2960,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 253,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 17
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.30059250000000004,
        "mean": 0.256004375,
        "median": 0.25514000000000003,
        "min": 0.2090225,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 17
        },
        "run_count": 16,
        "token_priced_attempt_count": 17,
        "total": 4.096070000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.17838885316056,
      "contributing_entrants": null,
      "distinct_rated_opponents": 194,
      "draws": 985,
      "eligibility_flag": true,
      "entry_count": 15,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:37Z",
      "losses": 977,
      "max_score": 52.5838024312028,
      "measured_at": null,
      "min_score": 12.448332398041078,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 0.9375,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2960,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.61765663046,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.59934779302218,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 998
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1406,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 267,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.08827968,
        "mean": 0.05437612,
        "median": 0.0574344,
        "min": 0.00733824,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.43500895999999994
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.20400839484258,
      "contributing_entrants": null,
      "distinct_rated_opponents": 162,
      "draws": 466,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:25:52Z",
      "losses": 482,
      "max_score": 71.62538316070135,
      "measured_at": null,
      "min_score": 10.977938094235043,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": 0.75,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1406,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.1821194799195,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.55283584941791,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 458
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 716,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3-flashx:746a19cef7ee23ef",
      "capped_draws": 58,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.01270098,
        "mean": 0.0085203375,
        "median": 0.007669445,
        "min": 0.00543595,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 10
        },
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.0681627
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.528031155574,
      "contributing_entrants": null,
      "distinct_rated_opponents": 151,
      "draws": 203,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:54Z",
      "losses": 288,
      "max_score": 57.68992736691443,
      "measured_at": null,
      "min_score": 7.915683771374111,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 716,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.0846377672417,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.528031155574,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 225
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3488,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 326,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.73533,
        "mean": 0.5886581249999999,
        "median": 0.58241,
        "min": 0.410635,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.709265
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.45233852196008,
      "contributing_entrants": null,
      "distinct_rated_opponents": 183,
      "draws": 988,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:30Z",
      "losses": 1319,
      "max_score": 59.326053968020524,
      "measured_at": null,
      "min_score": 11.142543596266535,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3488,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.3763603916655,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.45233852196008,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1181
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2786,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 290,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.179715,
        "mean": 0.09608781250000001,
        "median": 0.08063500000000001,
        "min": 0.0656625,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.7687025
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.34236797788512,
      "contributing_entrants": null,
      "distinct_rated_opponents": 186,
      "draws": 916,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:03:32Z",
      "losses": 1020,
      "max_score": 63.18239982783971,
      "measured_at": null,
      "min_score": 9.220151455961185,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2786,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.9157630074324,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.34236797788512,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 850
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2148,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3-flash:22cd36959459fbdd",
      "capped_draws": 310,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.0140393,
        "mean": 0.0037309874999999996,
        "median": 0.0024275875,
        "min": 0.001111625,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.029847899999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.18744561545431,
      "contributing_entrants": null,
      "distinct_rated_opponents": 183,
      "draws": 704,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:53:18Z",
      "losses": 805,
      "max_score": 63.151925655306094,
      "measured_at": null,
      "min_score": 11.498805673082217,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2148,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.6459344257833,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.18744561545431,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 639
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2160,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy4-preview:b8e7119f660161ad",
      "capped_draws": 243,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.028804516000000002,
        "mean": 0.015939765625,
        "median": 0.0150484685,
        "min": 0.009391185,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.127518125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.083880829330376,
      "contributing_entrants": null,
      "distinct_rated_opponents": 184,
      "draws": 727,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:00Z",
      "losses": 794,
      "max_score": 51.36592552964594,
      "measured_at": null,
      "min_score": 11.032703602266714,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": 1.0,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2160,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.1192351310904,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.083880829330376,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 639
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 7960,
      "canonical_public_row_identity": "publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 690,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 32,
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 13,
        "max": 0.1097735,
        "mean": 0.091486,
        "median": 0.08840574999999999,
        "min": 0.0773785,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8,
          "boardgame-list-prices-2026-09-08": 32
        },
        "recorded_attempt_count": 32,
        "run_count": 32,
        "token_priced_attempt_count": 8,
        "total": 2.927552
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 39.689127494925586,
      "contributing_entrants": null,
      "distinct_rated_opponents": 200,
      "draws": 846,
      "eligibility_flag": true,
      "entry_count": 19,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 19,
      "first_pass_rate": 0.59375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:30Z",
      "losses": 3675,
      "max_score": 52.03780039623947,
      "measured_at": null,
      "min_score": 18.275114149122885,
      "model_code_failure_rate": 0.40625,
      "model_code_failures": 13,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.59375,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 7960,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.4007513152198,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.83954362218033,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 3439
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3023,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 349,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.08884,
        "mean": 0.06562375000000001,
        "median": 0.062855,
        "min": 0.049908,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.52499
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.630660325327945,
      "contributing_entrants": null,
      "distinct_rated_opponents": 186,
      "draws": 951,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:27:18Z",
      "losses": 1168,
      "max_score": 49.82748733223222,
      "measured_at": null,
      "min_score": 9.60693783512406,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3022,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.0863684237786,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.630660325327945,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 903
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1606,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 204,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.14831665,
        "mean": 0.06589574925,
        "median": 0.044104765,
        "min": 0.0155414,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.527165994
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.5854146634512,
      "contributing_entrants": null,
      "distinct_rated_opponents": 177,
      "draws": 612,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:51Z",
      "losses": 497,
      "max_score": 71.170312983184,
      "measured_at": null,
      "min_score": 10.462135374510762,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1606,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.6989608362157,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.5854146634512,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 497
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1428,
      "canonical_public_row_identity": "publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 183,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.072978,
        "mean": 0.048872,
        "median": 0.046325000000000005,
        "min": 0.037309999999999996,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.390976
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.121648482195226,
      "contributing_entrants": null,
      "distinct_rated_opponents": 173,
      "draws": 385,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:26:28Z",
      "losses": 519,
      "max_score": 51.966061908297576,
      "measured_at": null,
      "min_score": 8.861174993521987,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1428,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.033819955415,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.545586455410955,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 524
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2238,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:14b865d3f352c468",
      "capped_draws": 142,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.01663094,
        "mean": 0.00499588742,
        "median": 0.0034890575,
        "min": 0.00258188,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.03996709936
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.45333427148738,
      "contributing_entrants": null,
      "distinct_rated_opponents": 184,
      "draws": 665,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:26:54Z",
      "losses": 851,
      "max_score": 53.29443897733345,
      "measured_at": null,
      "min_score": 13.18959924981592,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2235,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.8876963231307,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.45333427148738,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 719
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 636,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:9b3aa3914934b08c",
      "capped_draws": 72,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00414456,
        "mean": 0.0029296749999999996,
        "median": 0.00284053,
        "min": 0.00188342,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 12
        },
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.0234374
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.62005544829645,
      "contributing_entrants": null,
      "distinct_rated_opponents": 140,
      "draws": 174,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:55Z",
      "losses": 292,
      "max_score": 54.30649302297495,
      "measured_at": null,
      "min_score": 11.524793275000588,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": 0.875,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.2241957357637,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.45058527279682,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1520,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 43,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.190125,
        "mean": 0.15785312499999998,
        "median": 0.15388000000000002,
        "min": 0.131495,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.262825
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.51231631187023,
      "contributing_entrants": null,
      "distinct_rated_opponents": 174,
      "draws": 410,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:28:44Z",
      "losses": 532,
      "max_score": 65.98085473100755,
      "measured_at": null,
      "min_score": 9.918422916272286,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 93,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1520,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.067255671283,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.34638340505811,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 578
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2086,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:20c65e2b7513d4b4",
      "capped_draws": 348,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.39278997800000004,
        "mean": 0.1808710912875,
        "median": 0.13158330000000001,
        "min": 0.0448038366,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 1.4469687303
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.185104021864404,
      "contributing_entrants": null,
      "distinct_rated_opponents": 186,
      "draws": 661,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:03:32Z",
      "losses": 841,
      "max_score": 54.502993109011314,
      "measured_at": null,
      "min_score": 7.705163219117038,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 94,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2086,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.2517132222788,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.185104021864404,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 584
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 670,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max-0902:1a5946a1ae31cc68",
      "capped_draws": 92,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.212408,
        "mean": 0.12122175,
        "median": 0.11379500000000001,
        "min": 0.08249,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 10
        },
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.969774
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.088585523137525,
      "contributing_entrants": null,
      "distinct_rated_opponents": 158,
      "draws": 228,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:17:39Z",
      "losses": 234,
      "max_score": 71.7714779302936,
      "measured_at": null,
      "min_score": 2.3421974844057343,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 95,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 670,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.385584713357,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.088585523137525,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 208
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1738,
      "canonical_public_row_identity": "publication-row.v1:mixed:bytedance-seed-seed-2-0-code:2447db730c8d12fe",
      "capped_draws": 52,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.071558,
        "mean": 0.053513000000000005,
        "median": 0.0517895,
        "min": 0.034152,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.42810399999999993
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.14408027758309,
      "contributing_entrants": null,
      "distinct_rated_opponents": 173,
      "draws": 486,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-07"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:32Z",
      "losses": 658,
      "max_score": 75.43253351935807,
      "measured_at": null,
      "min_score": 9.226164992898436,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": 0.875,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": 96,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1738,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.9016719443946,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.990237218869844,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 594
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 3130,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 228,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.047757869999999994,
        "mean": 0.022448211274999998,
        "median": 0.017169796,
        "min": 0.0106770175,
        "recorded_attempt_count": 24,
        "run_count": 16,
        "total": 0.3591713804
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 33.97038612870208,
      "contributing_entrants": null,
      "distinct_rated_opponents": 192,
      "draws": 997,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:34:04Z",
      "losses": 1111,
      "max_score": 55.56765629222236,
      "measured_at": null,
      "min_score": 6.441669089116353,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 97,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3130,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.9505710990934,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.97038612870208,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1022
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 726,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:091b7e3f3afd6616",
      "capped_draws": 33,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.01198425,
        "mean": 0.00718913625,
        "median": 0.0061211025,
        "min": 0.005105595,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 10
        },
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.057513089999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.96387114069511,
      "contributing_entrants": null,
      "distinct_rated_opponents": 147,
      "draws": 168,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:21:57Z",
      "losses": 330,
      "max_score": 57.09922504114827,
      "measured_at": null,
      "min_score": 3.415118568191135,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": 1.0,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 98,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 726,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.416019408977,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.96387114069511,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 228
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 692,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max-0902:5961da4fe746e1db",
      "capped_draws": 60,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.278232,
        "mean": 0.1058585,
        "median": 0.088878,
        "min": 0.054514,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 10
        },
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.846868
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.83694392650825,
      "contributing_entrants": null,
      "distinct_rated_opponents": 157,
      "draws": 193,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:53Z",
      "losses": 278,
      "max_score": 54.31161562786239,
      "measured_at": null,
      "min_score": 16.575926558583998,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 99,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 691,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.590692556971,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.83694392650825,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 220
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": 7770,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 754,
      "codegen_cost_usd": {
        "admitted_cell_count": 28,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 42
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 42,
        "run_count": 30,
        "total": 0.0
      },
      "codegen_evaluated_cells": 30,
      "conditional_success_score": 33.934700850619244,
      "contributing_entrants": null,
      "distinct_rated_opponents": 200,
      "draws": 2779,
      "eligibility_flag": true,
      "entry_count": 28,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 19,
      "first_pass_rate": 0.6333333333333333,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:01Z",
      "losses": 2845,
      "max_score": 51.393316198139864,
      "measured_at": null,
      "min_score": 13.796926219903233,
      "model_code_failure_rate": 0.06666666666666667,
      "model_code_failures": 2,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": 0.9333333333333333,
      "provider": "Other",
      "provider_key": "other",
      "rank": 100,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 7756,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.6304550290656,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 9,
      "repaired_rate": 0.3,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.354406643828256,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 2132
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1478,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 188,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.21477374999999999,
        "mean": 0.17756265624999998,
        "median": 0.17285124999999998,
        "min": 0.1418975,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 1.42050125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.43999991037421,
      "contributing_entrants": null,
      "distinct_rated_opponents": 170,
      "draws": 414,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:14:31Z",
      "losses": 548,
      "max_score": 59.58082426309626,
      "measured_at": null,
      "min_score": 15.08141203859531,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 101,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1478,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.5491445609678,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.30927307032606,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 516
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2302,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:78fb6a9e00356b09",
      "capped_draws": 325,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.17384630544122162,
        "mean": 0.10235142090592425,
        "median": 0.0851321236175097,
        "min": 0.07156210251142602,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.8188113672473941
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.29577520839935,
      "contributing_entrants": null,
      "distinct_rated_opponents": 190,
      "draws": 851,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:14Z",
      "losses": 856,
      "max_score": 58.16040418419862,
      "measured_at": null,
      "min_score": 13.524183164803983,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 102,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2299,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.880784407659,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.29577520839935,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 592
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2851,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 309,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.011164349999999998,
        "mean": 0.00631805625,
        "median": 0.005847,
        "min": 0.00434295,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.050544450000000005
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.903427472866106,
      "contributing_entrants": null,
      "distinct_rated_opponents": 178,
      "draws": 953,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:41:54Z",
      "losses": 1091,
      "max_score": 55.929576936759275,
      "measured_at": null,
      "min_score": 16.646470580801548,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 103,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2850,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.7249486896628,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 32.903427472866106,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 806
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1500,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 225,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.03912625,
        "mean": 0.022799843750000003,
        "median": 0.021642500000000002,
        "min": 0.015285,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.18239875000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.87093314013739,
      "contributing_entrants": null,
      "distinct_rated_opponents": 167,
      "draws": 472,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:54:10Z",
      "losses": 588,
      "max_score": 59.48821171455273,
      "measured_at": null,
      "min_score": 15.277846845543255,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": 0.875,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 104,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1500,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.7731674081672,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 32.75888978070947,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 440
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1660,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 218,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.12185499999999999,
        "mean": 0.09110296875000001,
        "median": 0.09280125,
        "min": 0.0343775,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.72882375
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.82068922880934,
      "contributing_entrants": null,
      "distinct_rated_opponents": 181,
      "draws": 588,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:45Z",
      "losses": 545,
      "max_score": 72.93190187054188,
      "measured_at": null,
      "min_score": 10.664384932466085,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": 0.875,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 105,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1659,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.884354127069,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 32.71029546692019,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 526
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2346,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-6:aedb1b245d3cd53f",
      "capped_draws": 248,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.041774,
        "mean": 0.03185375,
        "median": 0.031432,
        "min": 0.027072,
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.25483
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.46340977658835,
      "contributing_entrants": null,
      "distinct_rated_opponents": 191,
      "draws": 859,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:19:40Z",
      "losses": 869,
      "max_score": 50.80866287227604,
      "measured_at": null,
      "min_score": 12.14033355812917,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 106,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2346,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.509435957214,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 32.46340977658835,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 618
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2914,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 152,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.03564825,
        "mean": 0.0239263125,
        "median": 0.02294625,
        "min": 0.01939525,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.19141049999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.31949261917336,
      "contributing_entrants": null,
      "distinct_rated_opponents": 191,
      "draws": 696,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:14:24Z",
      "losses": 1295,
      "max_score": 56.41476958488925,
      "measured_at": null,
      "min_score": 8.986553392204476,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": 107,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2914,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.1490833417463,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 32.31949261917336,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 923
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2246,
      "canonical_public_row_identity": "publication-row.v1:mixed:bytedance-seed-seed-2-0-code:c69120230888411c",
      "capped_draws": 296,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.075846,
        "mean": 0.050721249999999996,
        "median": 0.04471025,
        "min": 0.0372345,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.4057699999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.015952753786415,
      "contributing_entrants": null,
      "distinct_rated_opponents": 186,
      "draws": 768,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:21:34Z",
      "losses": 854,
      "max_score": 54.55419811458228,
      "measured_at": null,
      "min_score": 6.506552449736231,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": 1.0,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": 108,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2242,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.976131255616,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 32.015952753786415,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 620
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 6603,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 782,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.07826175,
        "mean": 0.05584070625,
        "median": 0.0541695,
        "min": 0.0411735,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 0.8934513
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 31.86715852062013,
      "contributing_entrants": null,
      "distinct_rated_opponents": 197,
      "draws": 2263,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 12,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:10:53Z",
      "losses": 2594,
      "max_score": 51.905912358610884,
      "measured_at": null,
      "min_score": 11.07482345464506,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 109,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6597,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.316512538555,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 31.86715852062013,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1740
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2984,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 243,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.07847,
        "mean": 0.06167125,
        "median": 0.061313,
        "min": 0.051588,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.4933699999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.62514039383202,
      "contributing_entrants": null,
      "distinct_rated_opponents": 187,
      "draws": 886,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:44:45Z",
      "losses": 1217,
      "max_score": 42.31219893783358,
      "measured_at": null,
      "min_score": 13.478477269301598,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 110,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2984,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.0844308593921,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 31.62514039383202,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 881
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2170,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-3:22ddc49b675eb171",
      "capped_draws": 275,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.043892749999999994,
        "mean": 0.023888718750000003,
        "median": 0.020423875,
        "min": 0.017614,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.19110975000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.068787453123537,
      "contributing_entrants": null,
      "distinct_rated_opponents": 187,
      "draws": 712,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:55Z",
      "losses": 830,
      "max_score": 47.149913347085835,
      "measured_at": null,
      "min_score": 13.707425405221867,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": 111,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2162,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.101072914798,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 31.068787453123537,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 620
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1808,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 188,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.09459400000000001,
        "mean": 0.0571955,
        "median": 0.043012,
        "min": 0.032534,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 0.457564
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.876939936900786,
      "contributing_entrants": null,
      "distinct_rated_opponents": 183,
      "draws": 620,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:04:41Z",
      "losses": 670,
      "max_score": 53.67468803008354,
      "measured_at": null,
      "min_score": 6.9862813021302,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 112,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1807,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.471458583072,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.876939936900786,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 517
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1528,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 115,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.007539277999999999,
        "mean": 0.0032457859375,
        "median": 0.0019568429999999998,
        "min": 0.001266762,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 0.031586439
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 32.87777735942499,
      "contributing_entrants": null,
      "distinct_rated_opponents": 186,
      "draws": 464,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.5555555555555556,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:55Z",
      "losses": 612,
      "max_score": 61.8142594407856,
      "measured_at": null,
      "min_score": 7.416920025051943,
      "model_code_failure_rate": 0.2222222222222222,
      "model_code_failures": 2,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": 0.7777777777777778,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 113,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1526,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.010866053009,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.875665898404755,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 450
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 2678,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 182,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.034210525000000006,
        "mean": 0.024715571875,
        "median": 0.0256067375,
        "min": 0.01676735,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 25
        },
        "run_count": 16,
        "token_priced_attempt_count": 25,
        "total": 0.39544914999999997
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 33.12559705121601,
      "contributing_entrants": null,
      "distinct_rated_opponents": 191,
      "draws": 512,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:41Z",
      "losses": 1160,
      "max_score": 57.82115624580523,
      "measured_at": null,
      "min_score": 10.746700809550001,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 114,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2676,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.6241452114477,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.8268415765198,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 1004
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1358,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 32,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.226689264,
        "mean": 0.16037539425,
        "median": 0.140728509,
        "min": 0.10689655,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 1.2830031539999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.88244772696924,
      "contributing_entrants": null,
      "distinct_rated_opponents": 167,
      "draws": 390,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-06"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:27:20Z",
      "losses": 458,
      "max_score": 51.93262612726081,
      "measured_at": null,
      "min_score": 10.785004751134416,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": 0.75,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 115,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1358,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.0233446208615,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.600565633888362,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 510
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 6376,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 790,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.0222516,
        "mean": 0.01697319375,
        "median": 0.015739925000000002,
        "min": 0.012759,
        "recorded_attempt_count": 34,
        "run_count": 16,
        "total": 0.27157109999999995
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 30.82157899867084,
      "contributing_entrants": null,
      "distinct_rated_opponents": 198,
      "draws": 1981,
      "eligibility_flag": true,
      "entry_count": 15,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:00Z",
      "losses": 2605,
      "max_score": 56.66854839969095,
      "measured_at": null,
      "min_score": 8.198390781857146,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.9375,
      "provider": "Google",
      "provider_key": "google",
      "rank": 116,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6369,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.6901992754015,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.32827456073786,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1783
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1906,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-glimmer-30b:085624a1bd2a3883",
      "capped_draws": 287,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.02351982,
        "mean": 0.019656965,
        "median": 0.019640945,
        "min": 0.01650772,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.15725572
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.350170089323683,
      "contributing_entrants": null,
      "distinct_rated_opponents": 187,
      "draws": 778,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:08:41Z",
      "losses": 657,
      "max_score": 45.37253694835636,
      "measured_at": null,
      "min_score": 15.966970879743966,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": 0.875,
      "provider": "Other",
      "provider_key": "other",
      "rank": 117,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1906,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.8301289045526,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.320887892682467,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 471
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 3011,
      "canonical_public_row_identity": "publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 485,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.00407402,
        "mean": 0.0029986699999999997,
        "median": 0.00314426,
        "min": 0.0012446800000000002,
        "recorded_attempt_count": 33,
        "run_count": 14,
        "total": 0.04176386
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 31.432327599551694,
      "contributing_entrants": null,
      "distinct_rated_opponents": 194,
      "draws": 935,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:09:29Z",
      "losses": 1207,
      "max_score": 46.950499952815655,
      "measured_at": null,
      "min_score": 10.592781159581312,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 2,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": 0.8571428571428571,
      "provider": "Other",
      "provider_key": "other",
      "rank": 118,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3002,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.4596568833645,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 5,
      "repaired_rate": 0.35714285714285715,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.244042856809923,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 860
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 708,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-6-luna:3dfecd4fa4d78509",
      "capped_draws": 71,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.0044690500000000005,
        "mean": 0.0038361124999999998,
        "median": 0.0037657374999999996,
        "min": 0.00283105,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.030688899999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.12942170206434,
      "contributing_entrants": null,
      "distinct_rated_opponents": 140,
      "draws": 216,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:14Z",
      "losses": 344,
      "max_score": 49.2610359164719,
      "measured_at": null,
      "min_score": 11.808719043622077,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 119,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 708,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.811079496877,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.12942170206434,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1540,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:45ec16f47504b5f5",
      "capped_draws": 275,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0508167,
        "mean": 0.02704530848,
        "median": 0.020221080000000002,
        "min": 0.01808105112,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.21636246784
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.779004608881248,
      "contributing_entrants": null,
      "distinct_rated_opponents": 181,
      "draws": 584,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-05"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:19:40Z",
      "losses": 630,
      "max_score": 57.44640162344343,
      "measured_at": null,
      "min_score": 18.481794861921347,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": 0.75,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 120,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1534,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.5828214183366,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 29.573696106452907,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 320
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1830,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:e0a2978fff9e81b1",
      "capped_draws": 268,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.01423672,
        "mean": 0.0073094338874999994,
        "median": 0.0062260825200000005,
        "min": 0.004397959999999999,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.0584754711
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.445418797781553,
      "contributing_entrants": null,
      "distinct_rated_opponents": 179,
      "draws": 707,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-05"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:59:44Z",
      "losses": 696,
      "max_score": 79.88316261692358,
      "measured_at": null,
      "min_score": 13.08582389461898,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.875,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 121,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1830,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.8547945237258,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 29.44584120542539,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 427
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1470,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 335,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.156555,
        "mean": 0.1422525,
        "median": 0.14850249999999998,
        "min": 0.12078,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.13802
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 29.975112307677914,
      "contributing_entrants": null,
      "distinct_rated_opponents": 177,
      "draws": 724,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:10:59Z",
      "losses": 443,
      "max_score": 49.045069424600065,
      "measured_at": null,
      "min_score": 12.771607546272488,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 122,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1469,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.2829276169302,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 28.990975719177527,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 302
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 5066,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 372,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 50
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0719635,
        "mean": 0.060768406250000004,
        "median": 0.0604727,
        "min": 0.05086675,
        "recorded_attempt_count": 50,
        "run_count": 16,
        "total": 0.9722945000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 29.825390658770534,
      "contributing_entrants": null,
      "distinct_rated_opponents": 194,
      "draws": 1284,
      "eligibility_flag": true,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.8125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:42Z",
      "losses": 2294,
      "max_score": 45.48522862689852,
      "measured_at": null,
      "min_score": 13.016216434051367,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 123,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5064,
      "rating_method": "sequential_elo",
      "raw_elo": 1376.5008103656928,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 28.84616969998549,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1486
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1356,
      "canonical_public_row_identity": "publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 60,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.09803328,
        "mean": 0.0253809975,
        "median": 0.00943521,
        "min": 0.00639384,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.20304798000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.376605494931567,
      "contributing_entrants": null,
      "distinct_rated_opponents": 172,
      "draws": 306,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:53:18Z",
      "losses": 601,
      "max_score": 42.47095379427678,
      "measured_at": null,
      "min_score": 8.021854667018928,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": 0.75,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 124,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1356,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.0152405891342,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 28.268616676610854,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 449
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 2000,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-terra:4506b3e0a8fb5629",
      "capped_draws": 305,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.136415,
        "mean": 0.07671781250000001,
        "median": 0.0705246875,
        "min": 0.058876874999999995,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.6137425000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 29.121872292278997,
      "contributing_entrants": null,
      "distinct_rated_opponents": 184,
      "draws": 820,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-05"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:25:05Z",
      "losses": 725,
      "max_score": 47.475109428289485,
      "measured_at": null,
      "min_score": 12.122561741654145,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 125,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2000,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.4835273318854,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 28.16574910066959,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 455
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1582,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro:c11fecb63644464d",
      "capped_draws": 282,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.03845835,
        "mean": 0.025296556802625002,
        "median": 0.02540433020275,
        "min": 0.014466934,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.20237245442100002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 29.985795436779895,
      "contributing_entrants": null,
      "distinct_rated_opponents": 173,
      "draws": 567,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-06"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:42Z",
      "losses": 563,
      "max_score": 44.02962894499428,
      "measured_at": null,
      "min_score": 14.507335399739189,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": 0.75,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 126,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1576,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.880059482926,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 27.904926937508936,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 446
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1510,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 215,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.1311545862,
        "mean": 0.0317000854,
        "median": 0.0104556789,
        "min": 0.0057139812,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.25360068319999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.551607363877064,
      "contributing_entrants": null,
      "distinct_rated_opponents": 176,
      "draws": 472,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:23:52Z",
      "losses": 621,
      "max_score": 47.29932137115699,
      "measured_at": null,
      "min_score": 4.615901320625215,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": 0.875,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 127,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1510,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.7441725839033,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 27.614206990564995,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 417
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1900,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:04d7da5a4f2e2af2",
      "capped_draws": 197,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00200925116,
        "mean": 0.0013339496149999998,
        "median": 0.0012586017,
        "min": 0.0008945895,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.01067159692
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.2443395218878,
      "contributing_entrants": null,
      "distinct_rated_opponents": 184,
      "draws": 548,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:18Z",
      "losses": 865,
      "max_score": 56.07127974669768,
      "measured_at": null,
      "min_score": 11.032375086013085,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.875,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 128,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1900,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.290362745103,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 27.31702730179655,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 487
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1232,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 187,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0097359,
        "mean": 0.0038356840999999994,
        "median": 0.0020557588,
        "min": 0.0014804776,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.030685472799999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 29.02881008054682,
      "contributing_entrants": null,
      "distinct_rated_opponents": 174,
      "draws": 254,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:33:38Z",
      "losses": 679,
      "max_score": 44.34870655763811,
      "measured_at": null,
      "min_score": 16.26871518944819,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.75,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 129,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1230,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.6201700821318,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 27.01435171490888,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 297
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1738,
      "canonical_public_row_identity": "publication-row.v1:mixed:openai-gpt-oss-120b:7e4ecfa424847773",
      "capped_draws": 215,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.015120192000000001,
        "mean": 0.0074424702499999995,
        "median": 0.006876,
        "min": 0.00134592,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.059539761999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 27.683808602948602,
      "contributing_entrants": null,
      "distinct_rated_opponents": 177,
      "draws": 640,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:12Z",
      "losses": 694,
      "max_score": 54.825621514346786,
      "measured_at": null,
      "min_score": 13.144887580099901,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 130,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1737,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.8254108981453,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.774899616201456,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 403
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2054,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:184634950256ca6a",
      "capped_draws": 290,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.050486600000000006,
        "mean": 0.0257422554375,
        "median": 0.02408436405,
        "min": 0.0093287,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.20593804349999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.625728338873593,
      "contributing_entrants": null,
      "distinct_rated_opponents": 182,
      "draws": 751,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:21:34Z",
      "losses": 855,
      "max_score": 44.37564898729753,
      "measured_at": null,
      "min_score": 10.068227975938049,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 131,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2054,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.0868717946837,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.625728338873593,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 448
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2184,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-flash:e1a2822fb5bba20e",
      "capped_draws": 291,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.006158996,
        "mean": 0.00343607875,
        "median": 0.002791493,
        "min": 0.0021123,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.027488630000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.59584737354384,
      "contributing_entrants": null,
      "distinct_rated_opponents": 191,
      "draws": 793,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:23Z",
      "losses": 952,
      "max_score": 56.77974293719396,
      "measured_at": null,
      "min_score": 8.785005477286392,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 132,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2184,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.6126849228663,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.59584737354384,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 439
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1342,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 208,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.13485595000000003,
        "mean": 0.031792056250000006,
        "median": 0.0158481,
        "min": 0.0111232,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 0.38919240000000005
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 28.154386641135257,
      "contributing_entrants": null,
      "distinct_rated_opponents": 163,
      "draws": 438,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-07"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.5555555555555556,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:33Z",
      "losses": 614,
      "max_score": 51.8801788071995,
      "measured_at": null,
      "min_score": 4.923730589416949,
      "model_code_failure_rate": 0.2222222222222222,
      "model_code_failures": 2,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": 0.7777777777777778,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 133,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1342,
      "rating_method": "sequential_elo",
      "raw_elo": 1309.2659363491496,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.43990881752858,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 290
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1874,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 239,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.07439860000000001,
        "mean": 0.060660574999999994,
        "median": 0.0565846,
        "min": 0.0485456,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.4852846000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.302156667515924,
      "contributing_entrants": null,
      "distinct_rated_opponents": 181,
      "draws": 706,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:01Z",
      "losses": 739,
      "max_score": 50.969829451519225,
      "measured_at": null,
      "min_score": 12.067201319254902,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 134,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1874,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.6055230564798,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.302156667515924,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 429
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 2564,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 181,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0721503,
        "mean": 0.03677837187500001,
        "median": 0.0324098875,
        "min": 0.01945095,
        "recorded_attempt_count": 39,
        "run_count": 16,
        "total": 0.5884539499999999
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 28.224103029781716,
      "contributing_entrants": null,
      "distinct_rated_opponents": 186,
      "draws": 768,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.4375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:34:28Z",
      "losses": 1140,
      "max_score": 59.97193472120926,
      "measured_at": null,
      "min_score": 9.390653049669545,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 135,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2562,
      "rating_method": "sequential_elo",
      "raw_elo": 1358.6958136472904,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.265487423313154,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 654
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 2532,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 291,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 27
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.01311555,
        "mean": 0.009215359375,
        "median": 0.009537575,
        "min": 0.004854125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 27
        },
        "run_count": 16,
        "token_priced_attempt_count": 27,
        "total": 0.14744575
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.883782722007982,
      "contributing_entrants": null,
      "distinct_rated_opponents": 188,
      "draws": 726,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-07"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:12Z",
      "losses": 1137,
      "max_score": 42.52477509866081,
      "measured_at": null,
      "min_score": 10.4996181061563,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 136,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2532,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.7801891533904,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.948783691247797,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 669
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2361,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 292,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.06806129999999999,
        "mean": 0.037113121874999995,
        "median": 0.0310111,
        "min": 0.0230335,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 10,
        "total": 0.38761484999999996
      },
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 27.23956902599473,
      "contributing_entrants": null,
      "distinct_rated_opponents": 181,
      "draws": 794,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.6,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:53Z",
      "losses": 1004,
      "max_score": 51.611716687770866,
      "measured_at": null,
      "min_score": 10.433188741667081,
      "model_code_failure_rate": 0.2,
      "model_code_failures": 2,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": 0.8,
      "provider": "Other",
      "provider_key": "other",
      "rank": 137,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2361,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.115355812149,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.2,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.761593839197328,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 563
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 3184,
      "canonical_public_row_identity": "publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 569,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 38
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.021206376000000002,
        "mean": 0.01337795025,
        "median": 0.01381146,
        "min": 0.006392298,
        "recorded_attempt_count": 38,
        "run_count": 16,
        "total": 0.214047204
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 26.51917609731877,
      "contributing_entrants": null,
      "distinct_rated_opponents": 195,
      "draws": 1040,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:09Z",
      "losses": 1368,
      "max_score": 41.60041525625513,
      "measured_at": null,
      "min_score": 7.685379769827811,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": 0.875,
      "provider": "Other",
      "provider_key": "other",
      "rank": 138,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3179,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.9607934211472,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.648504080267767,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 771
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1616,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 146,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.038769960000000006,
        "mean": 0.023744302225,
        "median": 0.0230069837,
        "min": 0.0074361952000000005,
        "recorded_attempt_count": 20,
        "run_count": 9,
        "total": 0.21411433159999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 27.013905664287595,
      "contributing_entrants": null,
      "distinct_rated_opponents": 178,
      "draws": 492,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:55Z",
      "losses": 708,
      "max_score": 38.134244776166305,
      "measured_at": null,
      "min_score": 11.887548577623754,
      "model_code_failure_rate": 0.2222222222222222,
      "model_code_failures": 2,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.7777777777777778,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 139,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1616,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.640561555621,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": 7,
      "repaired_rate": 0.7777777777777778,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.368878096087787,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 416
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1908,
      "canonical_public_row_identity": "publication-row.v1:mixed:mistralai-mistral-medium-3-5:8de2e9417bacc9d3",
      "capped_draws": 199,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 13
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.27741402547937455,
        "mean": 0.17469283299791016,
        "median": 0.15577176465417142,
        "min": 0.1042008119864669,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 13
        },
        "run_count": 8,
        "token_priced_attempt_count": 13,
        "total": 1.397542663983281
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.017320074855167,
      "contributing_entrants": null,
      "distinct_rated_opponents": 177,
      "draws": 719,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:28:48Z",
      "losses": 816,
      "max_score": 56.99034820792066,
      "measured_at": null,
      "min_score": 13.027941933509863,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": 0.875,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 140,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1902,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.1724393636034,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.16312488927676,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 367
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2008,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash:e1e7937be001cd2a",
      "capped_draws": 246,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.13084687320145388,
        "mean": 0.0871504498983802,
        "median": 0.08084431374719805,
        "min": 0.0619993303028941,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 0.6972035991870416
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 25.147294388704715,
      "contributing_entrants": null,
      "distinct_rated_opponents": 185,
      "draws": 675,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:59Z",
      "losses": 864,
      "max_score": 56.54349612359615,
      "measured_at": null,
      "min_score": 5.490992930648422,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 141,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2008,
      "rating_method": "sequential_elo",
      "raw_elo": 1332.2113954328536,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Minimal (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.147294388704715,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 469
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 4814,
      "canonical_public_row_identity": "publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 348,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 70
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.103943664,
        "mean": 0.0866474535,
        "median": 0.088847748,
        "min": 0.062759676,
        "recorded_attempt_count": 70,
        "run_count": 16,
        "total": 1.3863592560000002
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 26.99763459419179,
      "contributing_entrants": null,
      "distinct_rated_opponents": 195,
      "draws": 1249,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:12Z",
      "losses": 2341,
      "max_score": 36.90268984079009,
      "measured_at": null,
      "min_score": 11.64843348541389,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 142,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4767,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.0830957420344,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.12412993761782,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 46,
      "wins": 1177
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1111,
      "canonical_public_row_identity": "publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 212,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.11219570000000001,
        "mean": 0.0607572625,
        "median": 0.060057275,
        "min": 0.02174195,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.48605809999999994
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.20832575549643,
      "contributing_entrants": null,
      "distinct_rated_opponents": 161,
      "draws": 220,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:08:15Z",
      "losses": 609,
      "max_score": 42.50033505424671,
      "measured_at": null,
      "min_score": 11.850477367246295,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": 0.625,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 143,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1111,
      "rating_method": "sequential_elo",
      "raw_elo": 1242.901118933249,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.08114244133497,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 282
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 4607,
      "canonical_public_row_identity": "publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 729,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0068074,
        "mean": 0.0034371900000000006,
        "median": 0.00326368,
        "min": 0.00211404,
        "recorded_attempt_count": 35,
        "run_count": 14,
        "total": 0.04917795999999999
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 26.434769750155958,
      "contributing_entrants": null,
      "distinct_rated_opponents": 194,
      "draws": 1976,
      "eligibility_flag": true,
      "entry_count": 11,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-07"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:53Z",
      "losses": 1838,
      "max_score": 38.973297355450676,
      "measured_at": null,
      "min_score": 6.704785781203059,
      "model_code_failure_rate": 0.21428571428571427,
      "model_code_failures": 3,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": 0.7857142857142857,
      "provider": "Other",
      "provider_key": "other",
      "rank": 144,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4607,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.9124788726533,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 4,
      "repaired_rate": 0.2857142857142857,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 24.88809720804685,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 793
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 696,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:130c334db8df04f4",
      "capped_draws": 93,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.007391933999999999,
        "mean": 0.00359850675,
        "median": 0.003217359,
        "min": 0.00220635,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.028788053999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 24.77717097795133,
      "contributing_entrants": null,
      "distinct_rated_opponents": 165,
      "draws": 248,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:23Z",
      "losses": 327,
      "max_score": 39.43678310527615,
      "measured_at": null,
      "min_score": 11.271801424400126,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 145,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 696,
      "rating_method": "sequential_elo",
      "raw_elo": 1333.3426808937743,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 24.77717097795133,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 121
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1540,
      "canonical_public_row_identity": "publication-row.v1:mixed:openai-gpt-oss-120b:07d17099885c6bdb",
      "capped_draws": 245,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.002555,
        "mean": 0.001231986375,
        "median": 0.0010393855,
        "min": 0.00046744,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.009855891
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.57466175163876,
      "contributing_entrants": null,
      "distinct_rated_opponents": 179,
      "draws": 531,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:44:38Z",
      "losses": 687,
      "max_score": 45.228110399238034,
      "measured_at": null,
      "min_score": 9.845665543687444,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 146,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1540,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.6146599066324,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 24.730509355069742,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 322
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 3648,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 410,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.302804525,
        "mean": 0.259828169375,
        "median": 0.2529231275,
        "min": 0.22308452,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 4.15725071
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.48988573112342,
      "contributing_entrants": null,
      "distinct_rated_opponents": 187,
      "draws": 1167,
      "eligibility_flag": true,
      "entry_count": 9,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:44:38Z",
      "losses": 1726,
      "max_score": 53.98273918474334,
      "measured_at": null,
      "min_score": 8.759478344679279,
      "model_code_failure_rate": 0.4375,
      "model_code_failures": 7,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.5625,
      "provider": "Other",
      "provider_key": "other",
      "rank": 147,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3646,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.5096166882668,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.806939390284235,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 753
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 2234,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 233,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 25
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.00295601625,
        "mean": 0.0023887339375,
        "median": 0.002303478175,
        "min": 0.0017364400000000001,
        "recorded_attempt_count": 25,
        "run_count": 16,
        "total": 0.038219742999999994
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 25.728586433985495,
      "contributing_entrants": null,
      "distinct_rated_opponents": 186,
      "draws": 707,
      "eligibility_flag": true,
      "entry_count": 11,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.4375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:04:48Z",
      "losses": 946,
      "max_score": 44.49703925426421,
      "measured_at": null,
      "min_score": 6.460914561290655,
      "model_code_failure_rate": 0.3125,
      "model_code_failures": 5,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.6875,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 148,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2234,
      "rating_method": "sequential_elo",
      "raw_elo": 1325.809839820263,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.427939925025,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 581
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1798,
      "canonical_public_row_identity": "publication-row.v1:mixed:bytedance-seed-seed-2-0-code:e037862ab5c7ecb3",
      "capped_draws": 274,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.030187,
        "mean": 0.020951124999999998,
        "median": 0.0183875,
        "min": 0.0121355,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.167609
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 24.18388960192967,
      "contributing_entrants": null,
      "distinct_rated_opponents": 179,
      "draws": 538,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:52:14Z",
      "losses": 905,
      "max_score": 31.350179723882725,
      "measured_at": null,
      "min_score": 15.908866749062488,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": 0.875,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": 149,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1792,
      "rating_method": "sequential_elo",
      "raw_elo": 1250.312007575009,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.389889220372577,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 349
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1360,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 237,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.001632522,
        "mean": 0.00126739675,
        "median": 0.001232095,
        "min": 0.00090937,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.010139173999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 25.065186174186948,
      "contributing_entrants": null,
      "distinct_rated_opponents": 181,
      "draws": 598,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:27:20Z",
      "losses": 460,
      "max_score": 57.73838761870533,
      "measured_at": null,
      "min_score": 3.2968970313112287,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": 0.75,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 150,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1360,
      "rating_method": "sequential_elo",
      "raw_elo": 1381.4403929843977,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.32578404799714,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 302
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2058,
      "canonical_public_row_identity": "publication-row.v1:mixed:openai-gpt-oss-120b:59563b7e90e4a253",
      "capped_draws": 256,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.00145295,
        "mean": 0.001135709125,
        "median": 0.001180259,
        "min": 0.00078534,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.009085673
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 23.257439814922698,
      "contributing_entrants": null,
      "distinct_rated_opponents": 185,
      "draws": 742,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:01Z",
      "losses": 953,
      "max_score": 38.54712305704406,
      "measured_at": null,
      "min_score": 5.952533319730318,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 151,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2056,
      "rating_method": "sequential_elo",
      "raw_elo": 1297.8167190343195,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.257439814922698,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 361
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2292,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 273,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.01196465,
        "mean": 0.00854730625,
        "median": 0.008640199999999999,
        "min": 0.00555765,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 15
        },
        "recorded_attempt_count": 15,
        "run_count": 9,
        "total": 0.07763974999999998
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 23.891737064640214,
      "contributing_entrants": null,
      "distinct_rated_opponents": 181,
      "draws": 777,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.4444444444444444,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:11:37Z",
      "losses": 1072,
      "max_score": 57.00973194901733,
      "measured_at": null,
      "min_score": 4.881426142579081,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "Other",
      "provider_key": "other",
      "rank": 152,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2292,
      "rating_method": "sequential_elo",
      "raw_elo": 1286.9588560856132,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 4,
      "repaired_rate": 0.4444444444444444,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.19848351335541,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 443
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1362,
      "canonical_public_row_identity": "publication-row.v1:mixed:inception-mercury-2-5-preview:df3dbf369397b893",
      "capped_draws": 16,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0013895600000000002,
        "mean": 0.0009515637499999999,
        "median": 0.001025285,
        "min": 0.00044038,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.00761251
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.056088009018758,
      "contributing_entrants": null,
      "distinct_rated_opponents": 175,
      "draws": 549,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:09:48Z",
      "losses": 516,
      "max_score": 38.37213841472128,
      "measured_at": null,
      "min_score": 14.830792683984784,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": 0.625,
      "provider": "Other",
      "provider_key": "other",
      "rank": 153,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1361,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.6315089367552,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.167502406300063,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 296
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1128,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 218,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 21
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.065385,
        "mean": 0.03551179375,
        "median": 0.032728425,
        "min": 0.0200767,
        "recorded_attempt_count": 21,
        "run_count": 9,
        "total": 0.3177278
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 26.716578014107217,
      "contributing_entrants": null,
      "distinct_rated_opponents": 170,
      "draws": 416,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-05"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:05:04Z",
      "losses": 457,
      "max_score": 54.629833111248594,
      "measured_at": null,
      "min_score": 6.3532038338859245,
      "model_code_failure_rate": 0.4444444444444444,
      "model_code_failures": 4,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": 0.5555555555555556,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 154,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1128,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.9441498399137,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 5,
      "repaired_rate": 0.5555555555555556,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.065491033644633,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 255
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0597184625,
        "mean": 0.02467013555,
        "median": 0.0239011175,
        "min": 0.0040410944,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.1973610844
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 25.491686551767373,
      "contributing_entrants": null,
      "distinct_rated_opponents": 148,
      "draws": 593,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05",
        "GB2-07"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:03:41Z",
      "losses": 310,
      "max_score": 48.979799568566214,
      "measured_at": null,
      "min_score": 13.398467888140017,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.625,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 155,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1024,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.9768926712727,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 22.665670661087013,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 121
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2103,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 277,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.014791950000000002,
        "mean": 0.007616140625,
        "median": 0.005694875,
        "min": 0.00430875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 0.072064
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 23.22904400122249,
      "contributing_entrants": null,
      "distinct_rated_opponents": 180,
      "draws": 841,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.5555555555555556,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:05:49Z",
      "losses": 925,
      "max_score": 35.60527077189641,
      "measured_at": null,
      "min_score": 6.993147556840411,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "Other",
      "provider_key": "other",
      "rank": 156,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2096,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.2898984859337,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 3,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 22.555019454441762,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 330
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 5479,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 792,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 48
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0481474,
        "mean": 0.03800683125,
        "median": 0.037386975,
        "min": 0.02957195,
        "recorded_attempt_count": 48,
        "run_count": 16,
        "total": 0.6081093
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 22.738090266039418,
      "contributing_entrants": null,
      "distinct_rated_opponents": 196,
      "draws": 1872,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:29Z",
      "losses": 2656,
      "max_score": 38.59409823246796,
      "measured_at": null,
      "min_score": 12.559414245662259,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 157,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5468,
      "rating_method": "sequential_elo",
      "raw_elo": 1267.48924928716,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 21.99155806446691,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 940
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1658,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 246,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.03021,
        "mean": 0.0183815625,
        "median": 0.015581250000000001,
        "min": 0.01245825,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.1470525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 21.94285654112259,
      "contributing_entrants": null,
      "distinct_rated_opponents": 176,
      "draws": 730,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:36:58Z",
      "losses": 701,
      "max_score": 35.293552338742806,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 158,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1654,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.3642085222577,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 21.94285654112259,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 223
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1570,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-glimmer-30b:a614a905445f79d1",
      "capped_draws": 275,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.01024177,
        "mean": 0.0073127075,
        "median": 0.007628165,
        "min": 0.00402612,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.058501660000000004
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 23.31994578837838,
      "contributing_entrants": null,
      "distinct_rated_opponents": 177,
      "draws": 573,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-06"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:41:55Z",
      "losses": 705,
      "max_score": 34.62208396746334,
      "measured_at": null,
      "min_score": 6.328311136424571,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 159,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1570,
      "rating_method": "sequential_elo",
      "raw_elo": 1264.894672818974,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 21.701654864662462,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 292
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1968,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-glimmer-30b:20d2aea9e268d0ef",
      "capped_draws": 270,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.0138593,
        "mean": 0.00832475125,
        "median": 0.006849235,
        "min": 0.00556902,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.06659801
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 21.350513794117806,
      "contributing_entrants": null,
      "distinct_rated_opponents": 181,
      "draws": 767,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:24:59Z",
      "losses": 863,
      "max_score": 35.202863811457455,
      "measured_at": null,
      "min_score": 7.305194459653427,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": 160,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1968,
      "rating_method": "sequential_elo",
      "raw_elo": 1260.1453336549228,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 21.350513794117806,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 338
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 1867,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 362,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.0456916,
        "mean": 0.031545040625,
        "median": 0.035551075,
        "min": 0.01864685,
        "recorded_attempt_count": 35,
        "run_count": 16,
        "total": 0.50472065
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 24.21543621287482,
      "contributing_entrants": null,
      "distinct_rated_opponents": 188,
      "draws": 870,
      "eligibility_flag": true,
      "entry_count": 9,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:30Z",
      "losses": 689,
      "max_score": 37.7955878292642,
      "measured_at": null,
      "min_score": 8.523437707990063,
      "model_code_failure_rate": 0.4375,
      "model_code_failures": 7,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": 0.5625,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 161,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1867,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.5216328058705,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 20.971182924071233,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 308
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 2688,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 406,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.004911942999999999,
        "mean": 0.0031858331662499998,
        "median": 0.002947833025,
        "min": 0.001831717,
        "recorded_attempt_count": 24,
        "run_count": 16,
        "total": 0.05097333066
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 21.10390749270141,
      "contributing_entrants": null,
      "distinct_rated_opponents": 193,
      "draws": 931,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 10,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:08:41Z",
      "losses": 1267,
      "max_score": 35.616845403498495,
      "measured_at": null,
      "min_score": 5.504541378216173,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.875,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 162,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2688,
      "rating_method": "sequential_elo",
      "raw_elo": 1267.2566111789831,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 20.411028436546047,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 490
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2566,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 151,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.0057713,
        "mean": 0.004598475,
        "median": 0.0045067,
        "min": 0.0040101,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.0367878
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 19.663828504380618,
      "contributing_entrants": null,
      "distinct_rated_opponents": 182,
      "draws": 818,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:54Z",
      "losses": 1417,
      "max_score": 32.88038109999295,
      "measured_at": null,
      "min_score": 8.701180641503443,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 163,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2566,
      "rating_method": "sequential_elo",
      "raw_elo": 1242.382645008762,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 19.663828504380618,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 331
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1736,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 154,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 32
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0265755425,
        "mean": 0.018416099712499998,
        "median": 0.017703669999999998,
        "min": 0.0109615788,
        "recorded_attempt_count": 32,
        "run_count": 15,
        "total": 0.2720731754
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 21.503249649289508,
      "contributing_entrants": null,
      "distinct_rated_opponents": 176,
      "draws": 821,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.08333333333333333,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-03",
        "GB2-06",
        "GB2-07"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:53:41Z",
      "losses": 630,
      "max_score": 35.84961262725807,
      "measured_at": null,
      "min_score": 7.06835881817407,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 4,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.6666666666666666,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 164,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1736,
      "rating_method": "sequential_elo",
      "raw_elo": 1308.611184899834,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Medium (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": 7,
      "repaired_rate": 0.5833333333333334,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 19.430379467220693,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 285
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1436,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 206,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0149315,
        "mean": 0.0101355,
        "median": 0.010566625,
        "min": 0.00402875,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 0.081084
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 20.300581815650165,
      "contributing_entrants": null,
      "distinct_rated_opponents": 173,
      "draws": 371,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:59:57Z",
      "losses": 773,
      "max_score": 30.361355618251846,
      "measured_at": null,
      "min_score": 4.322931554682457,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 165,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1434,
      "rating_method": "sequential_elo",
      "raw_elo": 1179.1526666984132,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 18.891820080243768,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 290
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1119,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 157,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0422995,
        "mean": 0.027492531250000004,
        "median": 0.025548,
        "min": 0.0204145,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.21994025
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 21.107450358093807,
      "contributing_entrants": null,
      "distinct_rated_opponents": 164,
      "draws": 310,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:27:10Z",
      "losses": 614,
      "max_score": 29.827400148127907,
      "measured_at": null,
      "min_score": 14.9868688465287,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": 0.625,
      "provider": "Google",
      "provider_key": "google",
      "rank": 166,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1119,
      "rating_method": "sequential_elo",
      "raw_elo": 1195.8366238188325,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 18.767472185108453,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1304,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 47,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0154064,
        "mean": 0.00874386,
        "median": 0.0064215999999999995,
        "min": 0.00524064,
        "recorded_attempt_count": 13,
        "run_count": 9,
        "total": 0.08145696000000001
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 20.17038574595111,
      "contributing_entrants": null,
      "distinct_rated_opponents": 171,
      "draws": 436,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.4444444444444444,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:11:47Z",
      "losses": 644,
      "max_score": 43.55040400948236,
      "measured_at": null,
      "min_score": 9.261021826492382,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 3,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": 0.6666666666666666,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 167,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1301,
      "rating_method": "sequential_elo",
      "raw_elo": 1234.2952432543084,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 18.226000973624874,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 221
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1660,
      "canonical_public_row_identity": "publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 215,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.09705768000000001,
        "mean": 0.0730637925,
        "median": 0.07051098,
        "min": 0.05225028,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.58451034
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 18.8178035929424,
      "contributing_entrants": null,
      "distinct_rated_opponents": 172,
      "draws": 573,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:29:29Z",
      "losses": 791,
      "max_score": 41.673700863833744,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": 0.875,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 168,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1660,
      "rating_method": "sequential_elo",
      "raw_elo": 1220.7328187639591,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 7,
      "repaired_rate": 0.875,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 18.199981419636146,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 296
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1624,
      "canonical_public_row_identity": "publication-row.v1:mixed:inception-mercury-2-5-preview:ff9c957a999941a2",
      "capped_draws": 263,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0021869100000000002,
        "mean": 0.0013222775000000001,
        "median": 0.001054655,
        "min": 0.00083106,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.010578220000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 19.41544742908869,
      "contributing_entrants": null,
      "distinct_rated_opponents": 176,
      "draws": 716,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:30Z",
      "losses": 750,
      "max_score": 29.334163810673346,
      "measured_at": null,
      "min_score": 14.494975929834537,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 169,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1624,
      "rating_method": "sequential_elo",
      "raw_elo": 1249.700662697952,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 18.068109719151302,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 158
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1678,
      "canonical_public_row_identity": "publication-row.v1:mixed:mistralai-mistral-medium-3-5:e327e1c801399a5f",
      "capped_draws": 223,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.11538050836051075,
        "mean": 0.06762316700208985,
        "median": 0.06087263456058671,
        "min": 0.04290565490575157,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 12
        },
        "run_count": 8,
        "token_priced_attempt_count": 12,
        "total": 0.5409853360167187
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 18.520382849552355,
      "contributing_entrants": null,
      "distinct_rated_opponents": 180,
      "draws": 611,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-07"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:34:04Z",
      "losses": 862,
      "max_score": 32.358999465512234,
      "measured_at": null,
      "min_score": 3.83400018350949,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": 0.875,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 170,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1677,
      "rating_method": "sequential_elo",
      "raw_elo": 1247.6934407492552,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 17.91232553159492,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 204
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1510,
      "canonical_public_row_identity": "publication-row.v1:mixed:inception-mercury-2-5-preview:f07bc2e66f8341c5",
      "capped_draws": 212,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0025894200000000003,
        "mean": 0.0012652800000000001,
        "median": 0.000871045,
        "min": 0.00078866,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.010122240000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 19.06070636578836,
      "contributing_entrants": null,
      "distinct_rated_opponents": 175,
      "draws": 602,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:27:19Z",
      "losses": 741,
      "max_score": 25.490331698828758,
      "measured_at": null,
      "min_score": 10.772886758516659,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 171,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1509,
      "rating_method": "sequential_elo",
      "raw_elo": 1223.0001983376926,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 17.73798596192097,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 166
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1116,
      "canonical_public_row_identity": "publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 36,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.13491350000000002,
        "mean": 0.10247140625000001,
        "median": 0.113468875,
        "min": 0.061553000000000004,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.8197712500000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 19.1930133474309,
      "contributing_entrants": null,
      "distinct_rated_opponents": 167,
      "draws": 120,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:53Z",
      "losses": 774,
      "max_score": 28.39953999096173,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": 0.625,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 172,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1116,
      "rating_method": "sequential_elo",
      "raw_elo": 1135.9672594066092,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 17.065270226169293,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 222
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 2508,
      "canonical_public_row_identity": "publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 580,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 40
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 40,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 18.550407116525978,
      "contributing_entrants": null,
      "distinct_rated_opponents": 190,
      "draws": 1161,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-07"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:10:59Z",
      "losses": 1021,
      "max_score": 35.962389688777634,
      "measured_at": null,
      "min_score": 11.38300416268924,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 6,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": 0.625,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 173,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2506,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.4602134177467,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 16.493903511578825,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 324
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 980,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 46,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.00870475,
        "mean": 0.005883593750000001,
        "median": 0.006313125,
        "min": 0.003432,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.04706875
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 14.858192619973412,
      "contributing_entrants": null,
      "distinct_rated_opponents": 160,
      "draws": 233,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:26:38Z",
      "losses": 606,
      "max_score": 32.38410669171022,
      "measured_at": null,
      "min_score": 0.08310002118024254,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": 0.625,
      "provider": "Google",
      "provider_key": "google",
      "rank": 174,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 980,
      "rating_method": "sequential_elo",
      "raw_elo": 1103.9846183775826,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 13.211009003245497,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1732,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-3:650c1432bdd4728a",
      "capped_draws": 20,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.5256212,
        "mean": 0.38805244562499996,
        "median": 0.41839404999999996,
        "min": 0.063446985,
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 3.104419565
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 79.76036427478273,
      "contributing_entrants": null,
      "distinct_rated_opponents": 180,
      "draws": 193,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-04"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:12Z",
      "losses": 155,
      "max_score": 97.58127501121015,
      "measured_at": null,
      "min_score": 39.53484749867363,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1726,
      "rating_method": "sequential_elo",
      "raw_elo": 2029.3949496925354,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 79.76036427478273,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1378
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 522,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-7:f32f0106ab05aad6",
      "capped_draws": 2,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 7
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.4355744,
        "mean": 0.2698891428571428,
        "median": 0.2679664,
        "min": 0.0,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 6
        },
        "recorded_attempt_count": 7,
        "run_count": 7,
        "total": 1.889224
      },
      "codegen_evaluated_cells": 6,
      "conditional_success_score": 67.44242954428366,
      "contributing_entrants": null,
      "distinct_rated_opponents": 146,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-06"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:53:32Z",
      "losses": 87,
      "max_score": 81.37689077370601,
      "measured_at": null,
      "min_score": 57.56745440692937,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 522,
      "rating_method": "sequential_elo",
      "raw_elo": 1843.029216297003,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 67.44242954428366,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 417
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-7:08dd7ecb5fefd0b4",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 3,
        "cell_count": 5,
        "cost_basis_counts": {
          "provider_reported": 5
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.5756864,
        "mean": 0.31644575999999996,
        "median": 0.4788,
        "min": 0.0,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 3
        },
        "recorded_attempt_count": 5,
        "run_count": 5,
        "total": 1.5822288
      },
      "codegen_evaluated_cells": 3,
      "conditional_success_score": 61.511708255394375,
      "contributing_entrants": null,
      "distinct_rated_opponents": 96,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": 3,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 3,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:05:46Z",
      "losses": 58,
      "max_score": 65.39633278537028,
      "measured_at": null,
      "min_score": 58.418768085533685,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1771.826073378752,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 61.511708255394375,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 211
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 464,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:7f6340c5cd60d7e7",
      "capped_draws": 16,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 5,
        "cost_basis_counts": {
          "provider_reported": 5
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.1085880432,
        "mean": 0.08096321663999999,
        "median": 0.07468254,
        "min": 0.048483795,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 5
        },
        "recorded_attempt_count": 5,
        "run_count": 5,
        "total": 0.4048160832
      },
      "codegen_evaluated_cells": 5,
      "conditional_success_score": 59.63173372243593,
      "contributing_entrants": null,
      "distinct_rated_opponents": 132,
      "draws": 108,
      "eligibility_flag": false,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:50Z",
      "losses": 51,
      "max_score": 77.84906750984048,
      "measured_at": null,
      "min_score": 39.83045327654045,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": 1.0,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 464,
      "rating_method": "sequential_elo",
      "raw_elo": 1772.8510959796026,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 59.63173372243593,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 305
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1490,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-3:4bb11a89323f5400",
      "capped_draws": 3,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 7
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.273243,
        "mean": 0.18666160714285715,
        "median": 0.20966,
        "min": 0.0,
        "recorded_attempt_count": 7,
        "run_count": 7,
        "total": 1.30663125
      },
      "codegen_evaluated_cells": 6,
      "conditional_success_score": 54.58231057179747,
      "contributing_entrants": null,
      "distinct_rated_opponents": 178,
      "draws": 300,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-05"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:20:11Z",
      "losses": 386,
      "max_score": 77.02031061725003,
      "measured_at": null,
      "min_score": 16.539487456961396,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1489,
      "rating_method": "sequential_elo",
      "raw_elo": 1715.4859427661202,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 54.58231057179747,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 803
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 574,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max-0902:3772000f789711bc",
      "capped_draws": 71,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.606316,
        "mean": 0.33312575,
        "median": 0.357252,
        "min": 0.0,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 8
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 2.665006
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 54.36706229997475,
      "contributing_entrants": null,
      "distinct_rated_opponents": 150,
      "draws": 148,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.8571428571428571,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-07"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:55Z",
      "losses": 74,
      "max_score": 76.38881018245638,
      "measured_at": null,
      "min_score": 31.282600931503342,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 574,
      "rating_method": "sequential_elo",
      "raw_elo": 1708.5008524462214,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.14285714285714285,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 54.36706229997475,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 352
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 772,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-2:c4024993f2e98d89",
      "capped_draws": 52,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 2,
        "cost_basis_counts": {
          "provider_reported": 2
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.143734,
        "mean": 0.123945875,
        "median": 0.123945875,
        "min": 0.10415775,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 2
        },
        "recorded_attempt_count": 2,
        "run_count": 2,
        "total": 0.24789175
      },
      "codegen_evaluated_cells": 2,
      "conditional_success_score": 46.151515774593946,
      "contributing_entrants": null,
      "distinct_rated_opponents": 143,
      "draws": 96,
      "eligibility_flag": false,
      "entry_count": 2,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 2,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T12:26:40Z",
      "losses": 306,
      "max_score": 52.012365091494885,
      "measured_at": null,
      "min_score": 40.290666457693014,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 772,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.990422317601,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 46.151515774593946,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 370
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 400,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-4-1-nano:68d5f0be3c90fb50",
      "capped_draws": 73,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 1,
        "cost_basis_counts": {
          "estimated": 1,
          "local_standard_estimate": 1
        },
        "cost_is_complete": false,
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "max": 0.0023425,
        "mean": 0.0023425,
        "median": 0.0023425,
        "min": 0.0023425,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 1,
          "boardgame-list-prices-2026-09-08": 1
        },
        "recorded_attempt_count": 1,
        "run_count": 1,
        "token_priced_attempt_count": 1,
        "total": 0.0023425
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": 42.384495360660594,
      "contributing_entrants": null,
      "distinct_rated_opponents": 119,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": 1,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1-nano",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 1,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T04:52:57Z",
      "losses": 167,
      "max_score": 42.384495360660594,
      "measured_at": null,
      "min_score": 42.384495360660594,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 400,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.7109953757326,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Reasoning field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 42.384495360660594,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1986,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 53,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.6279041999999999,
        "mean": 0.526117125,
        "median": 0.5491332,
        "min": 0.330054,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 15
        },
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 4.208936999999999
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 43.19539960693221,
      "contributing_entrants": null,
      "distinct_rated_opponents": 180,
      "draws": 637,
      "eligibility_flag": false,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-05",
        "GB2-06"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.14285714285714285,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:07:06Z",
      "losses": 555,
      "max_score": 58.56757191941488,
      "measured_at": null,
      "min_score": 10.856245227633352,
      "model_code_failure_rate": 0.2857142857142857,
      "model_code_failures": 2,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 0.7142857142857143,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1974,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.606340835216,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 4,
      "repaired_rate": 0.5714285714285714,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 39.710512051870296,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 782
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1516,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-27b:47ad2584aeb815bb",
      "capped_draws": 151,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.079473456,
        "mean": 0.042855077875,
        "median": 0.0387132625,
        "min": 0.0,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.34284062299999996
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 42.524861260861684,
      "contributing_entrants": null,
      "distinct_rated_opponents": 176,
      "draws": 238,
      "eligibility_flag": false,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.2857142857142857,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:33:49Z",
      "losses": 700,
      "max_score": 57.945684696607124,
      "measured_at": null,
      "min_score": 25.78823504946214,
      "model_code_failure_rate": 0.2857142857142857,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": 0.7142857142857143,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1515,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.1938735317406,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 3,
      "repaired_rate": 0.42857142857142855,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 39.09407091889831,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 577
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash:a0af36e4d0bc99b5",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.122172,
        "mean": 0.06676931250000001,
        "median": 0.06893550000000001,
        "min": 0.025422,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.5341545000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.05240641667607,
      "contributing_entrants": null,
      "distinct_rated_opponents": 170,
      "draws": 257,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:59:45Z",
      "losses": 378,
      "max_score": 51.95111533508749,
      "measured_at": null,
      "min_score": 16.284282852755524,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 886,
      "rating_method": "sequential_elo",
      "raw_elo": 1358.6941480617518,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Low (historical request variant 1)",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 29.828125157274066,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 251
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5:707323710fb901e4",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 12
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.15380375000000002,
        "mean": 0.09741312500000002,
        "median": 0.090410625,
        "min": 0.06945125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 12
        },
        "run_count": 8,
        "token_priced_attempt_count": 12,
        "total": 0.779305
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.56397705047057,
      "contributing_entrants": null,
      "distinct_rated_opponents": 164,
      "draws": 281,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:55:04Z",
      "losses": 327,
      "max_score": 58.418681017299306,
      "measured_at": null,
      "min_score": 3.1304801359516308,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 836,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.0643293859027,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 29.373590415755068,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 228
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1712,
      "canonical_public_row_identity": "publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 284,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.03772852,
        "mean": 0.024905897500000003,
        "median": 0.026095300000000002,
        "min": 0.00984735,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.19924717999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.99334325098176,
      "contributing_entrants": null,
      "distinct_rated_opponents": 179,
      "draws": 316,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:41:47Z",
      "losses": 878,
      "max_score": 43.52073030334479,
      "measured_at": null,
      "min_score": 21.499809680072865,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": 0.5,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1708,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.7086739050835,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 28.584880482239612,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 514
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 954,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemma-4-31b-it:8d94257f5348b920",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0092087,
        "mean": 0.006571171428571429,
        "median": 0.00666192,
        "min": 0.00456754,
        "recorded_attempt_count": 15,
        "run_count": 7,
        "total": 0.0459982
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 30.60403246485289,
      "contributing_entrants": null,
      "distinct_rated_opponents": 144,
      "draws": 180,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-01"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:41:55Z",
      "losses": 475,
      "max_score": 50.26394857772395,
      "measured_at": null,
      "min_score": 19.990322662694933,
      "model_code_failure_rate": 0.42857142857142855,
      "model_code_failures": 3,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": 0.5714285714285714,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 952,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.5447305335833,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 4,
      "repaired_rate": 0.5714285714285714,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.60842335630734,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 297
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.0
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.324277808502853,
      "contributing_entrants": null,
      "distinct_rated_opponents": 179,
      "draws": 405,
      "eligibility_flag": false,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:17:53Z",
      "losses": 666,
      "max_score": 48.748765419591805,
      "measured_at": null,
      "min_score": 16.125411079300658,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1402,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.2287033547227,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.358710559150524,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 331
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 636,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-6-luna:dfbe27d870893a52",
      "capped_draws": 73,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 7,
        "cost_basis_counts": {
          "local_standard_estimate": 7
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.0030818,
        "mean": 0.0023309607142857143,
        "median": 0.0023213,
        "min": 0.00161355,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 7
        },
        "run_count": 7,
        "token_priced_attempt_count": 7,
        "total": 0.016316724999999997
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 25.376707397121997,
      "contributing_entrants": null,
      "distinct_rated_opponents": 143,
      "draws": 216,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-07"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:25:00Z",
      "losses": 319,
      "max_score": 47.74933846094135,
      "measured_at": null,
      "min_score": 10.200783051786512,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.7360625953631,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.376707397121997,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1622,
      "canonical_public_row_identity": "publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 392,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 8,
          "local_standard_estimate": 13
        },
        "cost_is_complete": false,
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.17217,
        "mean": 0.11039474999999999,
        "median": 0.10846,
        "min": 0.07562,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 13,
          "boardgame-list-prices-2026-09-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "token_priced_attempt_count": 13,
        "total": 0.8831579999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.37225226289518,
      "contributing_entrants": null,
      "distinct_rated_opponents": 177,
      "draws": 445,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:14:18Z",
      "losses": 878,
      "max_score": 37.04284479501129,
      "measured_at": null,
      "min_score": 15.926557852896163,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.5,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1622,
      "rating_method": "sequential_elo",
      "raw_elo": 1220.829991234879,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 22.176332390035217,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 299
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1372,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 225,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00391754,
        "mean": 0.0023617857142857143,
        "median": 0.00186618,
        "min": 0.00144036,
        "recorded_attempt_count": 8,
        "run_count": 7,
        "total": 0.0165325
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 22.312855735333248,
      "contributing_entrants": null,
      "distinct_rated_opponents": 167,
      "draws": 389,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.7142857142857143,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:10:59Z",
      "losses": 685,
      "max_score": 40.745990007722504,
      "measured_at": null,
      "min_score": 12.918261292629804,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 1,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": 0.8571428571428571,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1370,
      "rating_method": "sequential_elo",
      "raw_elo": 1211.2628902479948,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.14285714285714285,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 21.469328447914897,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 296
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1542,
      "canonical_public_row_identity": "publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 207,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 36
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.215758025,
        "mean": 0.16162675,
        "median": 0.1594081875,
        "min": 0.098579625,
        "recorded_attempt_count": 36,
        "run_count": 16,
        "total": 2.5860279999999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 25.922021453852462,
      "contributing_entrants": null,
      "distinct_rated_opponents": 175,
      "draws": 661,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:24:54Z",
      "losses": 550,
      "max_score": 64.55194498926986,
      "measured_at": null,
      "min_score": 0.10631171802151808,
      "model_code_failure_rate": 0.5625,
      "model_code_failures": 9,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": 0.4375,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1542,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.8685609279673,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 21.082076264331786,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 331
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 950,
      "canonical_public_row_identity": "publication-row.v1:mixed:stepfun-step-3-7-flash:dfa24619f0407197",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0711619,
        "mean": 0.039345212500000004,
        "median": 0.033877925,
        "min": 0.02387735,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.3147617
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 24.810268396923682,
      "contributing_entrants": null,
      "distinct_rated_opponents": 151,
      "draws": 400,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:11:58Z",
      "losses": 370,
      "max_score": 48.401795904394994,
      "measured_at": null,
      "min_score": 11.348188198383951,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": 0.5,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 950,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.1533183661343,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 20.862865756455648,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 658,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-27b:3dc939e9daa83d91",
      "capped_draws": 221,
      "codegen_cost_usd": {
        "admitted_cell_count": 3,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.045896320000000004,
        "mean": 0.021958409999999998,
        "median": 0.019045885,
        "min": 0.011539076,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.17566728
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 25.815872048344037,
      "contributing_entrants": null,
      "distinct_rated_opponents": 152,
      "draws": 396,
      "eligibility_flag": false,
      "entry_count": 2,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-05",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold",
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T06:12:20Z",
      "losses": 149,
      "max_score": 26.00270887896228,
      "measured_at": null,
      "min_score": 25.6290352177258,
      "model_code_failure_rate": 0.625,
      "model_code_failures": 5,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": 0.375,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 634,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.1732387178658,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 20.202011632004123,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 24,
      "wins": 89
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 2157,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 394,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 10,
        "max": 0.11839474,
        "mean": 0.07845433000000002,
        "median": 0.08046371000000001,
        "min": 0.036046930000000005,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 1.2552692799999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 23.298318032066064,
      "contributing_entrants": null,
      "distinct_rated_opponents": 187,
      "draws": 706,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:17Z",
      "losses": 1039,
      "max_score": 41.59139577501191,
      "measured_at": null,
      "min_score": 7.957773475504234,
      "model_code_failure_rate": 0.625,
      "model_code_failures": 10,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.375,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 2154,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.022066402523,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 18.231919146815006,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 409
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 52
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 52,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": 21.516338854208463,
      "contributing_entrants": null,
      "distinct_rated_opponents": 187,
      "draws": 706,
      "eligibility_flag": false,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.06666666666666667,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold",
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:34:04Z",
      "losses": 1299,
      "max_score": 38.44617773407611,
      "measured_at": null,
      "min_score": 2.780537548479402,
      "model_code_failure_rate": 0.6,
      "model_code_failures": 9,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": 0.4,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 2542,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.3355606204636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 5,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 17.111314480985172,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 537
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1196,
      "canonical_public_row_identity": "publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 350,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 30
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 30,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 21.057347774738698,
      "contributing_entrants": null,
      "distinct_rated_opponents": 165,
      "draws": 350,
      "eligibility_flag": false,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.1875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:26:38Z",
      "losses": 674,
      "max_score": 23.265561771241,
      "measured_at": null,
      "min_score": 18.67245084542328,
      "model_code_failure_rate": 0.6875,
      "model_code_failures": 11,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": 0.3125,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1192,
      "rating_method": "sequential_elo",
      "raw_elo": 1190.145486192457,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 15.744039665353446,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 168
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-row.v1:mixed:ibm-granite-granite-4-2-8b:d9f534c2d5f2138c",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.010999479999999999,
        "mean": 0.007405580000000001,
        "median": 0.00734207,
        "min": 0.0037107299999999998,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.05924464
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 20.205129732851056,
      "contributing_entrants": null,
      "distinct_rated_opponents": 91,
      "draws": 178,
      "eligibility_flag": false,
      "entry_count": 1,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T07:53:01Z",
      "losses": 68,
      "max_score": 20.205129732851056,
      "measured_at": null,
      "min_score": 20.205129732851056,
      "model_code_failure_rate": 0.875,
      "model_code_failures": 7,
      "model_display_name": "Granite 4.2 8B",
      "model_slug": "ibm-granite-granite-4-2-8b",
      "plugin_success_rate": 0.125,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.7415020745286,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Full",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Full",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Full",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 12.014042018929752,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 546,
      "canonical_public_row_identity": "publication-row.v1:mixed:ibm-granite-granite-4-2-8b:49a29e6f1bedcd1d",
      "capped_draws": 199,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.00272269,
        "mean": 0.001801155,
        "median": 0.001648355,
        "min": 0.00126116,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 0.01440924
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 11.70214905886831,
      "contributing_entrants": null,
      "distinct_rated_opponents": 138,
      "draws": 199,
      "eligibility_flag": false,
      "entry_count": 2,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:28:45Z",
      "losses": 335,
      "max_score": 22.686800313770597,
      "measured_at": null,
      "min_score": 0.7174978039660215,
      "model_code_failure_rate": 0.75,
      "model_code_failures": 6,
      "model_display_name": "Granite 4.2 8B",
      "model_slug": "ibm-granite-granite-4-2-8b",
      "plugin_success_rate": 0.25,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 546,
      "rating_method": "sequential_elo",
      "raw_elo": 1053.0817840368368,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 8.274668953981557,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-09-25T05:26:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 2278.825931725217,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 307
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 218,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-6-astra:af89b97f9d676a8c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 2196.543718849944,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 93.77364643873946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 211
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 310,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-09-25T05:16:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 310,
      "rating_method": "sequential_elo",
      "raw_elo": 2152.9795477867438,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 90.9620272870252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 290
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-6-astra:8883275fa81b106a",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T04:05:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 2100.9518948550194,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 87.05513481232872,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 226
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 218,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash:188028ef432c73f8",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-25T15:53:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 2084.7316454501633,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.75732154194154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 184
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-fable-5-1:d307977c9774b8cb",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-intensive",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T07:14:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 2002.0226474993385,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 79.87031463289088,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 203
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-fable-5-1:fdf38228456af115",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1957.9127540154252,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.72420952317101,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 195
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3:650c1432bdd4728a",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1945.0536760331718,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.80228272363448,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 382,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 75,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T14:16:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 382,
      "rating_method": "sequential_elo",
      "raw_elo": 1918.6768759763554,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.32458663155238,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 271
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-fable-5:9411c67711dccbe8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T06:19:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1918.3659092889625,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 73.84725078211831,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 186
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5-5:e7d2796533ceda7c",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-09-25T12:45:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1919.7275498220986,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.71748095253615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5-5:7dce3bfc0734dff8",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-09-25T12:46:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1914.6552626349105,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.31520041908865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 322,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-25T15:53:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 322,
      "rating_method": "sequential_elo",
      "raw_elo": 1889.1817125892937,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.07963331402082,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 250
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1895.2687657071344,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.98011275701009,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 141
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T14:02:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1872.6133126290345,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.24122372942317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash:79befaaad7974375",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T14:08:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1816.8108855019566,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.59984810877775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-3:4bb11a89323f5400",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T06:19:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1813.8305646022727,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.39429069545992,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-09-25T14:36:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.0464318648021,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.34042900452175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 235
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T13:07:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1797.8711663723197,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.07517251306582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3-flash:6bc93e3f26e0f0e5",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.3762702550496,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.06310136370395,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-fable-5-1:2ceef8038de90922",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-22T12:52:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1793.818548037135,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.05633016038571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 182
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-terra:bd3aacb7be18fc49",
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 45,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T13:19:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1794.308216479141,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.05600675030205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T02:40:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.2463407968028,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 64.97146846724627,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 207
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 650,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 256,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 230,
      "draws": 256,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 128,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 650,
      "rating_method": "sequential_elo",
      "raw_elo": 1781.376438319557,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 64.24089412492873,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 266
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3-flashx:d5d0648c410f1ae2",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.020483743773,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.73802956993577,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T14:08:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1763.003514868158,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.01830422379207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 232
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-terra:ac05ef4b9a51340d",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1762.4363561467956,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.7636226124865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 390,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 170,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 153,
      "draws": 170,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T16:04:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 389,
      "rating_method": "sequential_elo",
      "raw_elo": 1758.9180116522066,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.28494267530827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 186
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5-5:12d35a0c8ebcfc9f",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1773.4684559371246,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.15278254588686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 394,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 394,
      "rating_method": "sequential_elo",
      "raw_elo": 1747.7486728929528,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.09238331960013,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 230
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-7:f32f0106ab05aad6",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T12:45:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1770.0444447829527,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.986006568145754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 357,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T14:08:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1742.1375362854433,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.60666625896725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 324,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.867496603253,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.092745140918936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 237
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-fable-5:346aadd5d76b812b",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1739.0114851123444,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.0616104086017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 124
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-3:111be2eb4c7d6522",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-09-25T13:19:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1734.759712457236,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.756781153993344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 190,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-09-25T12:46:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1738.0389555080314,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.753181324378254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 122
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 132,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1725.375924521653,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.671054671727674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 213
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-8-flash:6b8b02f1f727feff",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-09-25T06:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1718.9045844132177,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.60452983725393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T07:41:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1720.3951004144337,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.48821171455273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 357,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 104,
      "max_score": null,
      "measured_at": "2026-09-25T05:05:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 357,
      "rating_method": "sequential_elo",
      "raw_elo": 1710.178254810776,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.326053968020524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 197
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-6-astra:9acce95ba71bd7c5",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1709.169890183018,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.93727047228494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 398,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 127,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 392,
      "rating_method": "sequential_elo",
      "raw_elo": 1698.6355858236166,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.56757191941488,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 223
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-7:08dd7ecb5fefd0b4",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1720.288436114733,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.418768085533685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5:707323710fb901e4",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T05:49:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1714.0103524224082,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.418681017299306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": null,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-27b:739c4d774075dc83",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-09-25T02:27:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1701.67334656394,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.407241304881026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 157
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 370,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 152,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 370,
      "rating_method": "sequential_elo",
      "raw_elo": 1705.0749290256176,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.364791089349026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 236
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1695.1065782809987,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.73838761870533,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 132
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-25T04:53:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1689.2694783053653,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.3097596033617,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 304,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3-flash:1540ade2fda6b881",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 304,
      "rating_method": "sequential_elo",
      "raw_elo": 1682.8213386192058,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.23829261695304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 201
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-fable-5:1f4ca1763387a608",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-09-25T12:05:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1676.2121600864764,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.519674933057175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 406,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T13:19:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 406,
      "rating_method": "sequential_elo",
      "raw_elo": 1651.1585365823491,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.18882050646197,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 225
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 634,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 122,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 267,
      "draws": 122,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 179,
      "max_score": null,
      "measured_at": "2026-09-25T04:53:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 634,
      "rating_method": "sequential_elo",
      "raw_elo": 1650.141425370019,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.925489222319115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 333
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T15:07:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.9125422305578,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.62351061515375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 144
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:9b3aa3914934b08c",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T12:05:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1664.6087584065551,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.30649302297495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T16:04:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 199,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.496353573131,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.67468803008354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3:9e30a36ab00bd740",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.22022848766,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.45667718141312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:d1c3d52890a12a42",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-09-25T07:56:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1641.1861002345797,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.44295115748309,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-2:c4024993f2e98d89",
      "capped_draws": 36,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 130,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-09-25T05:16:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.5185452601124,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.012365091494885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 198
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash:a0af36e4d0bc99b5",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.1516231006792,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Low (historical request variant 1)",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.95111533508749,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": null,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3:2dbca3140c06e14c",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T14:02:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.6235685063568,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.86956687787791,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 284,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-6:aedb1b245d3cd53f",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T14:36:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.9305849143425,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.80866287227604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 155
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-max-0902:3772000f789711bc",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.3499846972302,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.78300254547936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 130,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 130,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T07:41:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.6577112125444,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.73139480630345,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:b85a8fb56d024434",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T12:45:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.2608269926718,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.58183366585325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 468,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 136,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 150,
      "draws": 136,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 133,
      "max_score": null,
      "measured_at": "2026-09-25T16:03:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 468,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.8885398034024,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.39151672846605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 794,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 349,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 359,
      "max_score": null,
      "measured_at": "2026-09-25T16:04:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 794,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.345424331282,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.54900667277811,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 384
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 483,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 261,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 156,
      "draws": 261,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-25T06:04:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 483,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.0089674152905,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.48880202945978,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c37d073d6b142a09",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.4251198887735,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.334139920659695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy4-preview:2077a0aa15ce66b2",
      "capped_draws": 162,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 162,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.5488822308891,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.15370367716753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-6:bca3abc3bf41095f",
      "capped_draws": 69,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.8054293883342,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.914921531324325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-8-flash:83795e08736dcbd6",
      "capped_draws": 139,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 139,
      "draws": 139,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-09-23T17:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.2037897524815,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.40200930687758,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 753,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 230,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 252,
      "draws": 230,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 257,
      "max_score": null,
      "measured_at": "2026-09-25T13:19:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 750,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.8876848351229,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.08301890379797,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 263
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:2447db730c8d12fe",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.2246491961014,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.99394925717289,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-terra:4506b3e0a8fb5629",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 92,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.719470534291,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.475109428289485,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-09-25T06:46:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.923786506695,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.23098571326132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-2:20c65e2b7513d4b4",
      "capped_draws": 112,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 112,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 91,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.3621536320004,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.13787652878352,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:3fe477f1e3ed7e39",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T04:04:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.4873648676273,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.81148803602438,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 371,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 170,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 371,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.6692927335687,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.91146308402966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-8-flash:e50b23a03b02a00c",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-09-25T13:19:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.558062708041,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.63626796266691,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:b4ca94f8b60a9e88",
      "capped_draws": 104,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 133,
      "draws": 104,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.1200824179782,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.61493415632901,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:openai-gpt-oss-120b:07d17099885c6bdb",
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 48,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 156,
      "max_score": null,
      "measured_at": "2026-09-25T04:58:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.518874276408,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.228110399238034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d3192451477fbf98",
      "capped_draws": 202,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 202,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T04:38:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.1313317362046,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.02267217841239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3-flashx:746a19cef7ee23ef",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T04:04:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.3827439630202,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.65314846921031,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy4-preview:014a9ceb67d5b786",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 141,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.2996642393953,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.61529521482249,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-6:d94ddefd8b9f53eb",
      "capped_draws": 168,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 139,
      "draws": 168,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.1969563117673,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.46326454223426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-6-sol:a790476a054b6a1d",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.3851920559573,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.366545476309426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 1078,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 111,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 346,
      "draws": 111,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 434,
      "max_score": null,
      "measured_at": "2026-09-25T14:13:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 1078,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.3202629319196,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.356829595027115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 533
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 452,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 170,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 185,
      "max_score": null,
      "measured_at": "2026-09-25T03:01:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 452,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.1664104314107,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.374154056993305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 174
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.5348404139154,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.95850131307906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T12:45:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.5850112178202,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.54797429381968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 400,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-4-1-nano:68d5f0be3c90fb50",
      "capped_draws": 73,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1-nano",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 167,
      "max_score": null,
      "measured_at": "2026-09-25T04:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 400,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.7109953757326,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Reasoning field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.384495360660594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 362,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 150,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 139,
      "max_score": null,
      "measured_at": "2026-09-25T14:16:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 362,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.3205319946537,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.94845904405925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d0b5b92265541548",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.8060324709397,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.654809510966054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:78fb6a9e00356b09",
      "capped_draws": 110,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 110,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-09-25T07:41:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.8453959707654,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.34129805960164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.5486662112273,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.745990007722504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 880,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 228,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 373,
      "draws": 228,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 338,
      "max_score": null,
      "measured_at": "2026-09-25T15:07:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 880,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.3073110852486,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.52253717539108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 314
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 184,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.7279758888242,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.24576283638427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 218,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-22T15:56:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.627713228418,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.223782013343296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-09-25T00:11:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.6138129385795,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.14634293665803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 332,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-flash:98dfb2fac355b676",
      "capped_draws": 121,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 143,
      "draws": 121,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 119,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 332,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.6065705765584,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.08673683836688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:7f6340c5cd60d7e7",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.5833168613892,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.83045327654045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 310,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy4-preview:b8e7119f660161ad",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 157,
      "max_score": null,
      "measured_at": "2026-09-25T14:36:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 310,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.673031897578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.82178269174233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 107
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:130c334db8df04f4",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.2053512148998,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.43678310527615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:c69120230888411c",
      "capped_draws": 133,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 133,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T14:13:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.1846187113122,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.31602941916818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-27b:47ad2584aeb815bb",
      "capped_draws": 145,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 145,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-23T11:41:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.6059149220514,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.98414085011295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 464,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 146,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 230,
      "max_score": null,
      "measured_at": "2026-09-25T12:55:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 464,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.705955614129,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.973297355450676,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 111,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 111,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.1685015656856,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.84302075911713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-09-25T15:53:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.9041066181655,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.62063436503806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 958,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 157,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 301,
      "draws": 157,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 470,
      "max_score": null,
      "measured_at": "2026-09-25T13:25:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 958,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.1572038478112,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.59409823246796,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 331
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash:e1e7937be001cd2a",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.3242995992746,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Minimal (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.413011568160805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 155,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 155,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T13:39:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.3813504804746,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.358374606065006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 128,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 128,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T14:02:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.911565716598,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.19944229004737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 478,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 157,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 178,
      "draws": 157,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 177,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 478,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.5992831781336,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.44066886204282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 144
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 503,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 294,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 157,
      "draws": 294,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 117,
      "max_score": null,
      "measured_at": "2026-09-25T13:07:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 503,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.0231047535278,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.39954930655572,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-09-25T12:55:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.2533977452536,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.36361428580678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 141,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 141,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-25T13:39:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.9136376508068,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.24566499417282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-flash:14b865d3f352c468",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 190,
      "max_score": null,
      "measured_at": "2026-09-25T14:13:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.2691818857274,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.94050689253389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 407,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 204,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 407,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.931270627249,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.892139986097995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 400,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 139,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 199,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 400,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.965015024976,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.882220925455094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3-flashx:43f4326da261c154",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.1229581263374,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.075433997538745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:091b7e3f3afd6616",
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T04:10:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.4912292460306,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.02595884308104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 500,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 141,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 174,
      "draws": 141,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 214,
      "max_score": null,
      "measured_at": "2026-09-25T14:36:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 500,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.4078953975363,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.962389688777634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 866,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 168,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 278,
      "draws": 168,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 428,
      "max_score": null,
      "measured_at": "2026-09-25T14:16:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 866,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.2001559215114,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.948564706388524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 270
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 358,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 141,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 165,
      "max_score": null,
      "measured_at": "2026-09-25T16:04:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 358,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.725510285326,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.94035157388747,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 70,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 136,
      "draws": 70,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 163,
      "max_score": null,
      "measured_at": "2026-09-25T06:19:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.5791242479572,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.616845403498495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 75,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.239729616377,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.293552338742806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-2:4571486d5f3c5826",
      "capped_draws": 152,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 152,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T00:48:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.663118244126,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.93207694945243,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-glimmer-30b:a614a905445f79d1",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-09-25T04:00:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.763742153872,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.62208396746334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-3-flash:22cd36959459fbdd",
      "capped_draws": 153,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 125,
      "draws": 153,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-09-25T15:53:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.3289139357905,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.24431379862208,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-09-25T02:20:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.0647950863756,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.707552632427934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:45ec16f47504b5f5",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T13:19:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.1907061165489,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.41547564990715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-6-luna:3dfecd4fa4d78509",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.9606199703867,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.2677047708935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T13:25:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.2005538627475,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.22556272805624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.8380320982249,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.18568291274274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:openai-gpt-oss-120b:59563b7e90e4a253",
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 45,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 131,
      "max_score": null,
      "measured_at": "2026-09-25T06:24:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.5935344813565,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.899998911953496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 116,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.9109492803955,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.88541771484148,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-6-sol:a64b94562f86a4f3",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.892434022501,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.84684899959481,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-flash:e1a2822fb5bba20e",
      "capped_draws": 82,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.2251301931879,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.68634905445009,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-09-25T12:45:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.5738131724347,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.65331292775737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 117,
      "max_score": null,
      "measured_at": "2026-09-25T01:38:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1343.3023635597492,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.62683857968774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.1626289780015,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.577592074565786,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-6-luna:06fb6314cedafbae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.9508017642634,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.577483197926895,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c11fecb63644464d",
      "capped_draws": 88,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 88,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T04:53:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.2386768969225,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.55105506757531,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1340.3192343304647,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.37804159838408,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-glimmer-30b:085624a1bd2a3883",
      "capped_draws": 75,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T06:19:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.8405122937986,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.03694030645199,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 790,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 195,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 258,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 416,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 790,
      "rating_method": "sequential_elo",
      "raw_elo": 1327.1963781961763,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.942780295932366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:f9ec308f9bb8850b",
      "capped_draws": 111,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 111,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.9171005059115,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.754315907819613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-max-0902:1a5946a1ae31cc68",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T12:05:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.539448769024,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.73126434408019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 336,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 169,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 136,
      "draws": 169,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 126,
      "max_score": null,
      "measured_at": "2026-09-25T05:49:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 336,
      "rating_method": "sequential_elo",
      "raw_elo": 1331.7846951508814,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.50683596756701,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 123,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 123,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-09-24T06:12:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1310.2844110489343,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.361355618251846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-7:7805d7703d63f406",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.0210841058188,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.816492125257373,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 117,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 117,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 182,
      "max_score": null,
      "measured_at": "2026-09-25T03:11:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.3053028064285,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.67228693230946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:inception-mercury-2-5-preview:ff9c957a999941a2",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 81,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 147,
      "max_score": null,
      "measured_at": "2026-09-25T13:58:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1294.656689306476,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.334163810673346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 81,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T13:19:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1282.677883060552,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.35256079649359,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 194,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.1517867517532,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.092933810548693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 98,
      "max_score": null,
      "measured_at": "2026-09-25T15:53:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.528239817402,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Medium (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.235174943164314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-max-0902:5961da4fe746e1db",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1271.4328293956996,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.238232783733412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 118,
      "max_score": null,
      "measured_at": "2026-09-23T04:29:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1247.2566040724391,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.687756439022323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-3:22ddc49b675eb171",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 133,
      "max_score": null,
      "measured_at": "2026-09-25T05:05:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.071103594417,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.569331169607917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-6-luna:dfbe27d870893a52",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1258.2643758658196,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.36734015937674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 358,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 137,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 137,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 205,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 358,
      "rating_method": "sequential_elo",
      "raw_elo": 1234.1136208078292,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.196890039181877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-2:184634950256ca6a",
      "capped_draws": 75,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 117,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1232.2936928749032,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.693106006704642,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-flash:04d7da5a4f2e2af2",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 153,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1223.1473342222712,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.0769225264635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 416,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 148,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 163,
      "draws": 148,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 235,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 416,
      "rating_method": "sequential_elo",
      "raw_elo": 1222.5278976424986,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.894420756801225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 364,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 148,
      "draws": 76,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 201,
      "max_score": null,
      "measured_at": "2026-09-25T14:08:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1219.347261199558,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.51800550895544,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 85,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-09-25T16:03:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1234.61584720606,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.46942855390865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.385165364704298,
      "unilateral_faults": null,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 255,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 162,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 255,
      "rating_method": "sequential_elo",
      "raw_elo": 1211.6838207706028,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.309987292783003,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-glimmer-30b:20d2aea9e268d0ef",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 136,
      "max_score": null,
      "measured_at": "2026-09-25T07:14:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1208.4108885699306,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.0126853545906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 265,
      "max_score": null,
      "measured_at": "2026-09-25T13:39:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 386,
      "rating_method": "sequential_elo",
      "raw_elo": 1227.4780847101188,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.81526569038575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.54883454426297,
      "unilateral_faults": null,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:e037862ab5c7ecb3",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-09-25T13:25:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1201.7801698210126,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.505450352817086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro:42034002bcfc5f74",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 163,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1197.9967349311883,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.258235865851287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 150,
      "max_score": null,
      "measured_at": "2026-09-25T05:56:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1178.7263176583233,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.929347183423104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T04:00:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1170.1433865299655,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.07046347802326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 47,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 118,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1164.2895404365493,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.65077416582446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-flash:e0a2978fff9e81b1",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 152,
      "max_score": null,
      "measured_at": "2026-09-25T07:56:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1150.6627242367563,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.807057281000937,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 444,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 148,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 170,
      "draws": 148,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 253,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 444,
      "rating_method": "sequential_elo",
      "raw_elo": 1148.8249315169192,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.67245084542328,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1149.1878789322218,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.578517458993726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1126.8105583111628,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.963732521903303,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 120,
      "max_score": null,
      "measured_at": "2026-09-25T04:58:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1116.7667296118393,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.28451698383895,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 392,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 113,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 113,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 257,
      "max_score": null,
      "measured_at": "2026-09-25T13:25:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 392,
      "rating_method": "sequential_elo",
      "raw_elo": 1103.876733603052,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.926557852896163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 150,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 258,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1066.6378423386482,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.579978838993426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 139,
      "max_score": null,
      "measured_at": "2026-09-25T05:34:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1057.2574789116686,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.850477367246295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-6-sol:410ceff1171c2cf1",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1065.329091592359,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.206070516617746,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:mistralai-mistral-medium-3-5:e327e1c801399a5f",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 194,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 962.5786552315466,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 5.364102567773256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 208,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 954.7891752047293,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 4.881426142579081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-6-astra:af89b97f9d676a8c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 2063.9275630488323,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 219
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-fable-5-1:d307977c9774b8cb",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-intensive",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 2017.5102993445785,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 93.36562317213091,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 204
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-fable-5-1:2ceef8038de90922",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-09-25T05:18:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1958.7340226504202,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.0713065691807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 188
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-5-5:12d35a0c8ebcfc9f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1956.270414304034,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 82.7940575934645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-5-5:7dce3bfc0734dff8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1907.3870916629003,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.78826057875526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 136,
      "draws": 88,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1818.8505392710506,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.01945157758348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 245
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-6-astra:9acce95ba71bd7c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1807.7572388878887,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.90856632210667,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 146
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:tencent-hy4-preview:2077a0aa15ce66b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-09-25T15:33:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.1900957382898,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.51065884687536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-fable-5-1:fdf38228456af115",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T06:07:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.2960261882906,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.44955624043591,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 153
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:x-ai-grok-4-6:d94ddefd8b9f53eb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 227,
      "rating_method": "sequential_elo",
      "raw_elo": 1788.033141954644,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.09063610309277,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-fable-5:9411c67711dccbe8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1774.561902563198,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.21782579520304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1749.994117056542,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.64032909915444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:7f6340c5cd60d7e7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1737.3177663783688,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.95961453842323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 332,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 108,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T05:15:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 332,
      "rating_method": "sequential_elo",
      "raw_elo": 1715.609120411484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.53506842461099,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 197
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 496,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 194,
      "draws": 175,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 496,
      "rating_method": "sequential_elo",
      "raw_elo": 1717.3031610635599,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.28648284773156,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 278
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-5-5:e7d2796533ceda7c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T14:34:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1729.7987285584331,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.90073105067378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-6-astra:8883275fa81b106a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 121,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1708.023682150427,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.02617127882385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 149,
      "draws": 154,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 395,
      "rating_method": "sequential_elo",
      "raw_elo": 1673.9642494443597,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.759035246055106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 215
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 448,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 169,
      "draws": 188,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 448,
      "rating_method": "sequential_elo",
      "raw_elo": 1670.4433465530342,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.505919211020085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 228
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-8-flash:e50b23a03b02a00c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 97,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.5162560866765,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.106142336092056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-6-sol:410ceff1171c2cf1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1650.7341735576565,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.644601832444756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-3-flash:1540ade2fda6b881",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 121,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.8527377787163,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.574682510188765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-3:650c1432bdd4728a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 133,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.350599063675,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.53484749867363,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:3fe477f1e3ed7e39",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-09-25T06:53:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.2719135698069,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.622136291619164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 162,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T05:46:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.969068467395,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.36805948391099,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-fable-5:1f4ca1763387a608",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 140,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1610.0612275564356,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.08336866932161,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-6-luna:06fb6314cedafbae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.9847755272187,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.736737545406314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-3-flashx:43f4326da261c154",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.6787937426257,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.13947827988383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 352,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 182,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.403733556461,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.977282075387954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-2:20c65e2b7513d4b4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 122,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1588.4441487763484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.03910046349824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-6-sol:a64b94562f86a4f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.9785633907034,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.714134573439228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-8-max-0902:3772000f789711bc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.9174124025324,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.282600931503342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-terra:bd3aacb7be18fc49",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 140,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T05:31:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.9017626387488,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.58419652878032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-5-flash:188028ef432c73f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 145,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.2698824483814,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.850032552789482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 159,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.9709614984808,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.323646009270874,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:b85a8fb56d024434",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.7555095702419,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.984183127320136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:d1c3d52890a12a42",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-09-25T07:32:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.771308630353,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.34825360224334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:meta-muse-spark-1-3:111be2eb4c7d6522",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 152,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T05:15:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.6620961166543,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.121442848759003,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-8-flash:98dfb2fac355b676",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 157,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.3998389349945,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.898458456294655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:x-ai-grok-4-6:bca3abc3bf41095f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 160,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.649227789607,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.805218937462044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-2:4571486d5f3c5826",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 149,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.1895311928995,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.801661060669236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-3:2dbca3140c06e14c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 163,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.1569523858368,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.547509730974397,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 261,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 198,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T05:15:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 261,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.294948942284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.383109438871713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-3-flashx:d5d0648c410f1ae2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.5919741849273,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.229397698507874,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 274,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:f9ec308f9bb8850b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 202,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T06:45:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.2741551137517,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.63268358764324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-3-flash:6bc93e3f26e0f0e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 185,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.8617465400573,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.58473584796164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 218,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 142,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-18T19:19:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.1983241231044,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.212396895406123,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:b4ca94f8b60a9e88",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 159,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.068223724876,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.044287744530894,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-terra:ac05ef4b9a51340d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 233,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.6676710089532,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.25920994124026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-8-max-0902:5961da4fe746e1db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.4873472445463,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.199228787720973,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 372,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 125,
      "draws": 309,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.3153131129332,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.87963566446718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 814,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 257,
      "draws": 721,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 91,
      "max_score": null,
      "measured_at": "2026-09-25T14:02:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 814,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.251491718369,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.857571915656177,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:meta-muse-spark-1-3:22ddc49b675eb171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 197,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T05:15:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.5272225023564,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.693088932871294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 297,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.298834098546,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.646470580801548,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:78fb6a9e00356b09",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 204,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.1239013621373,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.550806400289524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:meta-muse-spark-1-3:4bb11a89323f5400",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 191,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.2377075518823,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.539487456961396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:x-ai-grok-4-7:7805d7703d63f406",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T14:34:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.5547550320823,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.534713974406596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 294,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 251,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T14:02:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 294,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.4655668165492,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.25613376182144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-6-sol:a790476a054b6a1d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.2233710793464,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.009012954450796,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:meta-muse-glimmer-30b:085624a1bd2a3883",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 232,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.5747369427895,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.966970879743966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 722,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 308,
      "draws": 549,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 98,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 722,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.8008998324374,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.804848105037715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 164,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T05:55:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.5097112982878,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.277846845543255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 333,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 265,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 333,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.226429295739,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.152435531238186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-8-flash:6b8b02f1f727feff",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 225,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.09447306829,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.032375698995798,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-3:9e30a36ab00bd740",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 249,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.4151588117313,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.003603712634062,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:inception-mercury-2-5-preview:ff9c957a999941a2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 245,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.7005581154203,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.879637514716912,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:inception-mercury-2-5-preview:df3dbf369397b893",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 235,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.00281933482,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.830792683984784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:x-ai-grok-4-6:aedb1b245d3cd53f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 201,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.1118446041532,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.478913384343024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-flash:e0a2978fff9e81b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 180,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T03:35:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.0772478703082,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.424491371108513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 348,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 272,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T07:49:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 348,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.2644727880233,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.95731578720957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 296,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 263,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.6194687642037,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.894809860305726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 192,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T12:33:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.0731425426543,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.849919257531704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 738,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 304,
      "draws": 601,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 113,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 738,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.2107804002305,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.796926219903233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:mistralai-mistral-medium-3-5:8de2e9417bacc9d3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 245,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.7289649498068,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.661100526328765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 335,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 118,
      "draws": 252,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 335,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.0048383762835,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.581319779736006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 201,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.3219932683191,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.522719036613323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 354,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 296,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 354,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.6825694962292,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.478477269301598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "draws": 157,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.166005128762,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.398467888140017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.132002100700243,
      "unilateral_faults": null,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-flash:14b865d3f352c468",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 213,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.7195443780645,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.18959924981592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:openai-gpt-oss-120b:7e4ecfa424847773",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 196,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.8502480309085,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.144887580099901,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-3-flash:22cd36959459fbdd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-23T12:55:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.7292650442894,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.04578932174765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 352,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 271,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.4601523846961,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.016216434051367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 193,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.4985349638378,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.984272900063827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 275,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.9628140050902,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.829263374876211,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 272,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-5-flash:79befaaad7974375",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 226,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.9520788257767,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.815210820746566,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 296,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 256,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.7146270238864,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.781594766493846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.100021197292,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.771607546272488,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 237,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T13:55:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 237,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.9517514652248,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.573076409935867,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 409,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 361,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T14:34:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 409,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.6811806382134,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.559414245662259,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 232,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.8149010053573,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.465517805734288,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 408,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 152,
      "draws": 364,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T14:03:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 408,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.0760154121217,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.448332398041078,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 211,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.3652676206952,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.402197288141299,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-terra:4506b3e0a8fb5629",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 248,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-09-25T06:15:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.192787296789,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.122561741654145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 220,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-24T19:00:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.1908067528893,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.067201319254902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:130c334db8df04f4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 87,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T07:40:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.070339189504,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.044306124648847,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:inception-mercury-2-5-preview:f07bc2e66f8341c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 217,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.2021984898463,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.973977531323163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 182,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.9417113371007,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.887548577623754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 280,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 232,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 280,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.9860199294324,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.88308300278399,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:openai-gpt-oss-120b:59563b7e90e4a253",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 208,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-09-25T05:15:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.1856422429778,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.830818971683568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-6-luna:3dfecd4fa4d78509",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.0091397204333,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.808719043622077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 129,
      "draws": 320,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.3376250866384,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.64843348541389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 218,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.756171592916,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.596795030322259,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:9b3aa3914934b08c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T07:23:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.8928882780958,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.524793275000588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 308,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.961299453459,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.50913920007812,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:stepfun-step-3-7-flash:dfa24619f0407197",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 204,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.4189027911261,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.348188198383951,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 202,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.4106515911064,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.23707888740107,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-8-max-0902:1a5946a1ae31cc68",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 76,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.3100352036117,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.176765516320527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 438,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 154,
      "draws": 381,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 438,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.028351726637,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Medium (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.169246623827902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 372,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 118,
      "draws": 301,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.5767306944488,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.142543596266535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 684,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 223,
      "draws": 603,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T04:02:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 683,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.9983873981048,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.07482345464506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 230,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T05:18:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.9943604324985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.053747422410106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:tencent-hy4-preview:b8e7119f660161ad",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 209,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.8518167627578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.032703602266714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-flash:04d7da5a4f2e2af2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 248,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-23T07:28:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.692555699686,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.032375086013085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.9764402657258,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.977938094235043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T01:45:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.4901507710395,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.9357408576404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 125,
      "draws": 302,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.6557046760618,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.856245227633352,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 159,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.0118488111527,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.851384971598858,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 191,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.2084405501407,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.746700809550001,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-pro:42034002bcfc5f74",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.5205440495274,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.705367299529621,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 200,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-23T01:24:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.788805327151,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.598572345430599,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 221,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.8164920623371,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.592781159581312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 454,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 160,
      "draws": 380,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 454,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.8231781524264,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.4996181061563,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 258,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.6576556254138,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.433188741667081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-6-luna:dfbe27d870893a52",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.591328719958,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.200783051786512,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d3192451477fbf98",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 176,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.736386569079,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.089425367998915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-2:184634950256ca6a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 212,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.7858282093537,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.068227975938049,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 182,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.6058873089435,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.918422916272286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 367,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 118,
      "draws": 296,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 367,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.8844189141503,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.898683790605384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 274,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d0b5b92265541548",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 225,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.8172875640382,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.851281775273819,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:openai-gpt-oss-120b:07d17099885c6bdb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 218,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.8613709181875,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.845665543687444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 266,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T07:23:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.0617383798524,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.754074770690439,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 340,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 285,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 340,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.6225297728333,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.60693783512406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 200,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.974428697136,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.390653049669545,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 216,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.5981193259827,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.261021826492382,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 180,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T12:47:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.5307445622263,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.242992989536942,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5:707323710fb901e4",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 120,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T03:24:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.6050675512174,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.227503285322296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:2447db730c8d12fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 208,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.6064511381016,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.226164992898436,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c37d073d6b142a09",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T02:14:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.717879979862,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.212833783417654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 182,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.0571705946704,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.167843583998868,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 185,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.2500566846154,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.062637566537523,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 296,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 231,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T05:23:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.7663744997578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.986553392204476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-8-flash:e1a2822fb5bba20e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 228,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.8842249110578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.785005477286392,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 384,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 337,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-23T22:15:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 382,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.3826257930446,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.759478344679279,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 388,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 149,
      "draws": 336,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 388,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.916593140943,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.523437707990063,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-fable-5:346aadd5d76b812b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 174,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T03:09:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.3571447074532,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.30135369548809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.8860565669552,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.220985627441877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 674,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 217,
      "draws": 597,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 674,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.7182649446754,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.198390781857146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:c69120230888411c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 208,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.1822389925464,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.075838704215268,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 189,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.9106514889643,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.021854667018928,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-3-flashx:746a19cef7ee23ef",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.9878730014084,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.915683771374111,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 215,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T02:29:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.9765137394702,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.685379769827811,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 184,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T12:33:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.9560390913514,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.4721350280143835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-8-flash:83795e08736dcbd6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 198,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.631198326482,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.419192145713985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 165,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.6240175501182,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.416920025051943,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:meta-muse-glimmer-30b:20d2aea9e268d0ef",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 230,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T05:30:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.1719021757642,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.305194459653427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 174,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.6961790820071,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.460914561290655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 428,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 150,
      "draws": 371,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 428,
      "rating_method": "sequential_elo",
      "raw_elo": 1400.7656812982682,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.441669089116353,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 416,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 151,
      "draws": 337,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 416,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.5143585817068,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 5.504541378216173,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-5-flash:e1e7937be001cd2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 212,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.7833269162336,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Minimal (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 5.490992930648422,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 180,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T06:15:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.9531513092209,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 4.615901320625215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:mistralai-mistral-medium-3-5:e327e1c801399a5f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 200,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.3171666207907,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 3.83400018350949,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:091b7e3f3afd6616",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.6076019714485,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 3.415118568191135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 170,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.6914103410684,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 3.2968970313112287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 8,
      "draws": 294,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.579899262466,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 2.780537548479402,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.75890625908325,
      "unilateral_faults": null,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 175,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.284192320307,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.10631171802151808,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-6-astra:af89b97f9d676a8c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-09-25T07:40:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 2163.5190039337767,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 227
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-fable-5-1:d307977c9774b8cb",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-intensive",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 448,
      "rating_method": "sequential_elo",
      "raw_elo": 2059.1206107382654,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 90.12297537243145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 409
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 111,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T13:18:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 2057.4923993127013,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 89.1770885247866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.48567977499789805,
      "unilateral_faults": 0,
      "wins": 240
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-3:650c1432bdd4728a",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 2002.6753583822758,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 84.96955467101989,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-fable-5-1:2ceef8038de90922",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-09-25T15:05:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1972.416702123303,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 82.02730182911166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 196
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-fable-5-1:fdf38228456af115",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 48,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T03:10:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1964.727780037505,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.26175197390472,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 162
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-6-astra:9acce95ba71bd7c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T12:55:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1963.0600032369164,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.14783522356228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 159
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-5-5:12d35a0c8ebcfc9f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1944.5287804487727,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.19523136118757,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-6-sol:410ceff1171c2cf1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1899.422086219661,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.72412581235643,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 125,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 297,
      "rating_method": "sequential_elo",
      "raw_elo": 1878.832615588344,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.60400026322671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 252
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-5-5:7dce3bfc0734dff8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1879.3579016389629,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.06960818323918,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:b4ca94f8b60a9e88",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 102,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1853.5765514492996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.85712897377837,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-fable-5:9411c67711dccbe8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-24T21:02:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1832.5446903752695,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.91099828064931,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 144
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-8-flash:6b8b02f1f727feff",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T15:52:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.5667967296579,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.42521343604795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 157
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-3-flash:1540ade2fda6b881",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1769.4036597862491,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.99601875550448,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 310,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 309,
      "rating_method": "sequential_elo",
      "raw_elo": 1755.6663153829472,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.971421270163184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 245
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-3:2dbca3140c06e14c",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 223,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.032721767681,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.655310442580365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 146
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-8-flash:e50b23a03b02a00c",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 231,
      "rating_method": "sequential_elo",
      "raw_elo": 1734.0510593713882,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.606732398356996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 144
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-6-astra:8883275fa81b106a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 105,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-23T11:59:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1731.0450240140724,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.39056563515839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1255,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 503,
      "draws": 209,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 252,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 1067,
      "rating_method": "sequential_elo",
      "raw_elo": 1714.6275748238265,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.64563528194297,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 182,
      "wins": 606
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-7:f32f0106ab05aad6",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T06:45:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1737.3085217737114,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.56745440692937,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-6:bca3abc3bf41095f",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T05:08:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1703.2849728497006,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.698811869129386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-3-flash:6bc93e3f26e0f0e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T07:24:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 235,
      "rating_method": "sequential_elo",
      "raw_elo": 1702.8455834195784,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.69463597353327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash:188028ef432c73f8",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1691.0453258781433,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.60089993691927,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 104,
      "max_score": null,
      "measured_at": "2026-09-25T04:09:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 317,
      "rating_method": "sequential_elo",
      "raw_elo": 1670.9434445351742,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.03507393286738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 175
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-6-sol:a64b94562f86a4f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1686.2818549800577,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.69038122461175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-3-flashx:43f4326da261c154",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T14:10:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1681.9417056415027,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.44037344594306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:tencent-hy4-preview:b8e7119f660161ad",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 91,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T13:18:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.8815906793627,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.36592552964594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-09-25T14:34:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.6919382738752,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.2458282828391,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 196
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-6-sol:a790476a054b6a1d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.5182096935155,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.59414597637835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-3:4bb11a89323f5400",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T05:09:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 231,
      "rating_method": "sequential_elo",
      "raw_elo": 1635.343723849433,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.32890841701454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:tencent-hy4-preview:2077a0aa15ce66b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-09-25T13:18:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.8637733818819,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.95177486372414,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-max-0902:3772000f789711bc",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T14:01:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.8364247304644,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.941446429504964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d0b5b92265541548",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-09-25T12:11:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.6780053004868,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.221073631451,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 132
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 338,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 104,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-09-25T04:31:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 337,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.251265689971,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.17183438241479,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash:79befaaad7974375",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T13:06:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 227,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.1792080783332,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.096115949915344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 247,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 97,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 247,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.2689260067089,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.73709363383094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.68086849439,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.508144083646044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 106,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T07:53:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 315,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.8305710643456,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.028376243947854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1829,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 61,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 7,
      "distinct_rated_opponents": 802,
      "draws": 332,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 669,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 1814,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.5361152807309,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.23380903288835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 813
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 288,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-8-flash:83795e08736dcbd6",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T13:13:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 287,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.390800807944,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.40886149683821,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-flash:98dfb2fac355b676",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 233,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.579881000369,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.1842635007645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-max-0902:5961da4fe746e1db",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T14:01:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.8608992836625,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.60300379005268,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 340,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-09-25T12:11:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 337,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.8806387963914,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.59139577501191,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-27b:47ad2584aeb815bb",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 319,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.817412312884,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.52872346510729,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-3:22ddc49b675eb171",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-09-25T12:55:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.5875613105047,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.321044443306036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 128
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 392,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-2:c4024993f2e98d89",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 160,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 392,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.4622993750897,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.290666457693014,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 826,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 278,
      "draws": 234,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 276,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 825,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.465897364233,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.96263207896568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 315
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T15:52:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.4368423578528,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.68914114822327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:b85a8fb56d024434",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.8733133898322,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.21094528138139,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:d1c3d52890a12a42",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.9882420820213,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.11467185215879,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:3fe477f1e3ed7e39",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T14:10:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.8354628199563,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.89535829138528,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 692,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 230,
      "draws": 146,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 301,
      "max_score": null,
      "measured_at": "2026-09-25T13:34:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 690,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.108182778877,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.68882139766329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 243
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 184,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 116,
      "max_score": null,
      "measured_at": "2026-09-25T13:00:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 390,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.6866651776409,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.017147044794186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 386,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 144,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 127,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 386,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3910495421942,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.69758041750218,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-6:d94ddefd8b9f53eb",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 81,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.1119937212918,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.55815458856067,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 121
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 154,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-25T13:00:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 395,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.4678989558154,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.5386599849108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-3:111be2eb4c7d6522",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.4157889641933,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.22845180963232,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 157,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.6170637154105,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.09937739195498,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-3-flashx:d5d0648c410f1ae2",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T14:01:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.789130216092,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.86266928865096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:f9ec308f9bb8850b",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-09-25T14:34:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 267,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.3015602204446,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.833760249546316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 70,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.0560424806201,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.70563172240146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-3-flash:22cd36959459fbdd",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 78,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-09-25T04:46:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.0873289037993,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.69837664699844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 140,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T15:05:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.9918204527644,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.60527077189641,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 114,
      "draws": 105,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-09-25T14:34:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.886419174509,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.84294341860225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-5-5:e7d2796533ceda7c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T14:34:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.622548247758,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.34311959065729,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-max-0902:1a5946a1ae31cc68",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-25T06:08:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.9820140457375,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.06465240673219,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 750,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 256,
      "draws": 167,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 296,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 750,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.2227097154012,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.923231532018065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 287
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-3:9e30a36ab00bd740",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 112,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T05:09:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 289,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.613537643171,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.884063520036406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 115,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 137,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 379,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.0058603990226,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.73006163008332,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T15:52:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.2483969765071,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.72939172603578,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 324,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-pro:42034002bcfc5f74",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 135,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 104,
      "max_score": null,
      "measured_at": "2026-09-25T07:24:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.3723474587694,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.70168001380781,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 121,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-09-25T05:01:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.788672542698,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.4132006443893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 358,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 149,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-09-25T15:05:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 357,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.0595086507585,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.11276640129881,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 390,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 169,
      "max_score": null,
      "measured_at": "2026-09-25T13:13:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 390,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.579434924167,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.401398518164704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:mistralai-mistral-medium-3-5:e327e1c801399a5f",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T05:33:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.5594912825875,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.358999465512234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 404,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 139,
      "draws": 104,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 141,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 404,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.7398947124789,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.35563973235182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 159
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T14:10:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.4993993868663,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.20690745467834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-flash:e1a2822fb5bba20e",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 85,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.4048742590476,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.195227382686326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 126,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.666548535275,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.12861045665751,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:45ec16f47504b5f5",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 122,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.0292175090588,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.090831635554785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2040,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 106,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 8,
      "distinct_rated_opponents": 890,
      "draws": 988,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 616,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 2027,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.8573400456446,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.960500358147634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 423
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.5735751880513,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.852211767076273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 430,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 147,
      "draws": 157,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 151,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 430,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.299023042923,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.713474611999153,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-6:aedb1b245d3cd53f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 210,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.6513321364587,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.50159332277543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-glimmer-30b:085624a1bd2a3883",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 111,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T05:13:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.0818669469777,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.333463916130018,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:20c65e2b7513d4b4",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T16:03:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.2081191859868,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.24083392559777,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:78fb6a9e00356b09",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 146,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T04:36:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 311,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.7987684691807,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.16093776611165,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 114,
      "draws": 110,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-09-25T05:53:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.1559244502741,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.064861623987174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.8522727272727293,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d3192451477fbf98",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 48,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 159,
      "max_score": null,
      "measured_at": "2026-09-25T15:05:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.901306966007,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.898756018461224,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 107
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-6-luna:3dfecd4fa4d78509",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.6104458381499,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.790788087810803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 454,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 150,
      "draws": 111,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 175,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 454,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.7131334740745,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.57889546605584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 168
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:openai-gpt-oss-120b:7e4ecfa424847773",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 94,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T14:10:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 237,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.1661562967663,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.416960415799508,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:e037862ab5c7ecb3",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 86,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 118,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.1205357785889,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.93788889353827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-glimmer-30b:a614a905445f79d1",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 105,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T07:53:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.400539154845,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.72211236651506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 161,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 161,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.9895234122694,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.69551968181914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 378,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 165,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 125,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 377,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.2127966123949,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.60871326724313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 372,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 188,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T15:05:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.4553692437319,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.602746818470994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 155,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.2724687641871,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.590881232571984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 367,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 135,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 144,
      "max_score": null,
      "measured_at": "2026-09-25T12:23:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 367,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.26332903877,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.399378159658458,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:openai-gpt-oss-120b:07d17099885c6bdb",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T13:00:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.73409700549,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.30577418243054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 816,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 268,
      "draws": 315,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 333,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 816,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.2676204995091,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.209728963258087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 168
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-terra:bd3aacb7be18fc49",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 97,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T13:01:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.6974052765618,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.152984788095484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T02:18:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.3571775918304,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.006158947241175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-flash:14b865d3f352c468",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 127,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T12:49:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 227,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.7977828302849,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.919565896920982,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:mistralai-mistral-medium-3-5:8de2e9417bacc9d3",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 91,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.3861199840924,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.792321610997423,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:tencent-hy4-preview:014a9ceb67d5b786",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 147,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T12:49:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 227,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.637968070786,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.716557872593558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:c69120230888411c",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 109,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-25T13:13:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.4737461688474,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.37320291516669,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 286,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 76,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T05:38:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.7927382313237,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.343796015821606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 245,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 91,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 91,
      "max_score": null,
      "measured_at": "2026-09-25T04:46:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 245,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.3932195649575,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.03443283640638,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:inception-mercury-2-5-preview:df3dbf369397b893",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 137,
      "max_score": null,
      "measured_at": "2026-09-25T07:24:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 327,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.361021000484,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.88259281471392,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-6-luna:dfbe27d870893a52",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T06:23:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.2373577118456,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.683992349793055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-6-luna:06fb6314cedafbae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.7374212036264,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.32497239731715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 386,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 139,
      "draws": 173,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 142,
      "max_score": null,
      "measured_at": "2026-09-25T12:11:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 383,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.944398778814,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.96684174359192,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 253,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 120,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 253,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.7745011547036,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.886410274650494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-3-flashx:746a19cef7ee23ef",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.0109907047743,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.803693368013082,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:9b3aa3914934b08c",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T14:16:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.5447175645834,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.648906753764663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 393,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 137,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 142,
      "max_score": null,
      "measured_at": "2026-09-25T12:54:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 389,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.71380781756,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.396024096701737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.545911650451,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.151875896013834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c11fecb63644464d",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T13:18:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1376.0391416548625,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.992442624160834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-fable-5:346aadd5d76b812b",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 112,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.2619874653299,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.909155462658255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 304,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "draws": 121,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 118,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 304,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.1594077190425,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.58413890549305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:184634950256ca6a",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 92,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T07:53:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.407686783745,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.46312383770164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:091b7e3f3afd6616",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.8720480178501,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.43721144686283,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 89,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-09-25T12:55:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.2044232021271,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.41165252574357,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 86,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-23T18:02:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.539693708129,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.363492385352973,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 354,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 150,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 115,
      "max_score": null,
      "measured_at": "2026-09-25T12:55:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 353,
      "rating_method": "sequential_elo",
      "raw_elo": 1361.9795528555346,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.104629327422128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 372,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 97,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 150,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.9441679487495,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.4009168781914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.4504891862682,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.393147755638637,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T15:52:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.9903528332513,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.38530689431558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.0584808767833,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.184427349708432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:2447db730c8d12fe",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 131,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.1997656077283,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.1673833049802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 701,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 232,
      "draws": 301,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 254,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 700,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.9246507141288,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.680993596380297,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:openai-gpt-oss-120b:59563b7e90e4a253",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 96,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-09-25T14:01:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.1217167129957,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.640132783464484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 593,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 219,
      "draws": 232,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 224,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 592,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.950691072303,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.486121890739962,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.526619811048,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.81853039406397,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-flash:04d7da5a4f2e2af2",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 97,
      "max_score": null,
      "measured_at": "2026-09-25T07:40:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.0969046013313,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.41588826786613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-flash:e0a2978fff9e81b1",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 103,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1332.266627525364,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.86788153475712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 143,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1339.318229141879,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.82884738650803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:130c334db8df04f4",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.197069141969,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.61403769326364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-terra:4506b3e0a8fb5629",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1327.5418566566275,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.392271275872172,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 166,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-09-25T16:03:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.6202852830872,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.097043119894657,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-09-25T07:53:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.8177773893021,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.796958527790924,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T13:18:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1322.0768677527358,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.29269496662492,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:ibm-granite-granite-4-2-8b:d9f534c2d5f2138c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 178,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T07:53:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Granite 4.2 8B",
      "model_slug": "ibm-granite-granite-4-2-8b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.7415020745286,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Full",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Full",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Full",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.205129732851056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 81,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1307.8369821715016,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.08692079482323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 179,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-09-25T05:39:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1291.6982265647202,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.358096814846906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 394,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 124,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 180,
      "max_score": null,
      "measured_at": "2026-09-25T05:53:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 394,
      "rating_method": "sequential_elo",
      "raw_elo": 1288.1863481775406,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.275114149122885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 204,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-24T21:12:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1291.6821137938018,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.86950861804385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.4651870198682,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.509396641546054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-glimmer-30b:20d2aea9e268d0ef",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1283.4809249094064,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.341929439664884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T13:13:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1290.242440849019,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.32053682080132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-terra:ac05ef4b9a51340d",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 119,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T05:08:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1283.2051660127208,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.192155362935345,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T05:30:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1282.0012952043824,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.325386867061756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 10,
      "draws": 45,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1306.1751192514726,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.125411079300658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.6794725589981,
      "unilateral_faults": null,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash:e1e7937be001cd2a",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 143,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1261.2317498439854,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Minimal (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.19108200229045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-fable-5:1f4ca1763387a608",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 142,
      "max_score": null,
      "measured_at": "2026-09-25T12:54:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1248.3349928557948,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.925660427832574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:4571486d5f3c5826",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 113,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 104,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1235.62536608604,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.731041209161488,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c37d073d6b142a09",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-09-25T13:18:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1233.2156802078318,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.557760361514816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 143,
      "draws": 137,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 191,
      "max_score": null,
      "measured_at": "2026-09-25T14:16:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.463984346276,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.11442709036542,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5:707323710fb901e4",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T13:06:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1147.9746125679014,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 3.1304801359516308,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": null,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 362,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 90,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 251,
      "max_score": null,
      "measured_at": "2026-09-25T13:06:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 362,
      "rating_method": "sequential_elo",
      "raw_elo": 1094.6246645220451,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-6-astra:af89b97f9d676a8c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-18T18:46:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1971.8262474267835,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 97.3475278073704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 208
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-6-astra:9acce95ba71bd7c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T13:06:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1961.1956366893105,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 95.69162884853398,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-5-5:12d35a0c8ebcfc9f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1938.5493344877893,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 90.00227559221021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-fable-5:9411c67711dccbe8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 235,
      "rating_method": "sequential_elo",
      "raw_elo": 1893.5270627446387,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.53702993381843,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-6-astra:8883275fa81b106a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1892.848210716588,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.4755448688683,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 182
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-fable-5-1:d307977c9774b8cb",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-intensive",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 470,
      "rating_method": "sequential_elo",
      "raw_elo": 1881.2969682397602,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 83.69072312275135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 391
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1824.75684458976,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.61817300254005,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 234
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 400,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 142,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T12:27:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 400,
      "rating_method": "sequential_elo",
      "raw_elo": 1822.8530033140737,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.54068913938104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 292
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T15:33:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 311,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.4129004500003,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.23925278736691,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 208
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-3-flash:6bc93e3f26e0f0e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-24T22:57:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.060755450437,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.92301827974818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 152
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-5-5:7dce3bfc0734dff8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1805.3403032296576,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.8950709756612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-3:2dbca3140c06e14c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 245,
      "rating_method": "sequential_elo",
      "raw_elo": 1783.7259066666843,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.04383353117605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 188
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:x-ai-grok-4-7:f32f0106ab05aad6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1791.0168893205353,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.52073299307726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-3-flash:1540ade2fda6b881",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1766.1518146573342,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.33514913196505,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 156
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-max-0902:3772000f789711bc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1764.5604542591154,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.02862383954646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-6-sol:410ceff1171c2cf1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-09-25T03:35:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1755.6273778628556,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.103159443224804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-27b:739c4d774075dc83",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1699.05144103761,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.3162952972934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-3-flashx:43f4326da261c154",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 85,
      "rating_method": "sequential_elo",
      "raw_elo": 1715.2006324965307,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.03914060818941,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.16638660171921,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:b85a8fb56d024434",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1712.5593249631836,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.52382996903797,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-fable-5-1:fdf38228456af115",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1690.6042668268888,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.829742723095954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 362,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 109,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 362,
      "rating_method": "sequential_elo",
      "raw_elo": 1682.9100428921965,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.50674408464692,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 702,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 313,
      "draws": 235,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 91,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 702,
      "rating_method": "sequential_elo",
      "raw_elo": 1686.5855614897616,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.29144742349905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 376
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:7f6340c5cd60d7e7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1691.7277889611023,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.745857819297356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-6-sol:a64b94562f86a4f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T05:30:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1688.9460438675994,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.257540853318176,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-5-5:e7d2796533ceda7c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1663.7707762059795,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.386745340440996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:3fe477f1e3ed7e39",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.517725810686,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.35844545212433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 241,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 102,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 241,
      "rating_method": "sequential_elo",
      "raw_elo": 1615.0006829372037,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.54396182565621,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 720,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 238,
      "draws": 230,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 183,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 717,
      "rating_method": "sequential_elo",
      "raw_elo": 1594.8571569382302,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.20004663167366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 304
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 315,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 163,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T07:49:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.9896839264163,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.38810520024291,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-3-flash:22cd36959459fbdd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 95,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T06:00:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.7774749008704,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.72860683637134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:x-ai-grok-4-6:bca3abc3bf41095f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 99,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.3811214442503,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.93009393174424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-6-luna:06fb6314cedafbae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-09-25T05:36:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1588.7967516245444,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.761198585719725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-8-flash:6b8b02f1f727feff",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 155,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-25T06:45:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.4731006614738,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.71773602229773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:meta-muse-spark-1-3:111be2eb4c7d6522",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 100,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.6391068559133,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.67974117462816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-5-flash:79befaaad7974375",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 132,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.0629310889913,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.351623972760336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:x-ai-grok-4-6:d94ddefd8b9f53eb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 137,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 82,
      "max_score": null,
      "measured_at": "2026-09-25T06:00:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.2109146893276,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.57744830171936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 204,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 86,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T06:53:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.1828199120182,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.48092158803702,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-2:4571486d5f3c5826",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 117,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-22T19:25:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.907977907179,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.346174295769494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-flash:98dfb2fac355b676",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 154,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T06:45:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.878576748059,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.57117101283803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-2:20c65e2b7513d4b4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 88,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-09-25T15:34:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.1922997177962,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.06169697877685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:tencent-hy4-preview:2077a0aa15ce66b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 115,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.201890822483,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.959581269225342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 438,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 161,
      "draws": 159,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 127,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 438,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.3568685365676,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.879083926934985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 152
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 340,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 181,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 340,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.6188990359437,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.758173635715277,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 121,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.4178925941112,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.558055123630105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-3-flashx:d5d0648c410f1ae2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.8372344019856,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.002702443895366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 207,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.447010417425,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.499312490995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 412,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 191,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 119,
      "max_score": null,
      "measured_at": "2026-09-25T06:45:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 412,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.0655350180587,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.46384306521568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 762,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 312,
      "draws": 399,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 166,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 762,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.7841618976643,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.904976519441306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 197
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-fable-5-1:2ceef8038de90922",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 107,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.3418830394744,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.6720155573788,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:meta-muse-glimmer-30b:085624a1bd2a3883",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 169,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-09-25T05:13:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.4979397865784,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.427715764746406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 116,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.031259469797,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.407809820471147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-fable-5:1f4ca1763387a608",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 127,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-09-25T07:49:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.571534971346,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.320051355957688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 858,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 349,
      "draws": 517,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 197,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 857,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.243403122604,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.26787091915678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-27b:3dc939e9daa83d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 175,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T06:12:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.9071604016394,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.00270887896228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 122,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.002911542282,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.703543197148946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T05:23:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 209,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.2986589973464,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.19033659038525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 158,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.7851386586212,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.567731347266125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:091b7e3f3afd6616",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.0835524827144,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.435827804187948,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 142,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.7428807986598,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.02215444542085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:inception-mercury-2-5-preview:df3dbf369397b893",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 212,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-24T04:00:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.1967676463596,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.217326577705883,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 880,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 287,
      "draws": 494,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 218,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 873,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.5207476530259,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.726966280556393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 362,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 155,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 362,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.1095908237608,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.083742425713893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 322,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 186,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 322,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.2184540066644,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.758731660036542,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 149,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-09-25T07:32:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.6023650157663,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.354567805952815,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-pro:42034002bcfc5f74",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 142,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.6180884228831,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.2316997815558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-8-flash:e50b23a03b02a00c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 107,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 233,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.2382047303836,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.023257576979688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:meta-muse-glimmer-30b:20d2aea9e268d0ef",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 185,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.097484815574,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.956344911843157,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 418,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 130,
      "draws": 264,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-09-25T05:46:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 418,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.5491498281401,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.86000846438864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-3:9e30a36ab00bd740",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 171,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T15:55:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.468110312634,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.741133901363547,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-3-flashx:746a19cef7ee23ef",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.482847789648,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.713672394721467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-6-luna:3dfecd4fa4d78509",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.212853956462,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.377750187081375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-8-flash:83795e08736dcbd6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 126,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.9671886659755,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.23603223004519,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:f9ec308f9bb8850b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 220,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T03:43:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.07008301429,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.184495234374975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemma-4-31b-it:8d94257f5348b920",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 180,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T04:44:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.2757496518636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.990322662694933,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:b4ca94f8b60a9e88",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 136,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T15:55:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.8734672756627,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.985371794844777,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c37d073d6b142a09",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 169,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.1220332328212,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.91598677885711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 349,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.5444548730766,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.525005417352162,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 129,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.3635699825543,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.522920844339357,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 153,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T05:23:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.0056731801114,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.29660629832776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 149,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-09-23T03:30:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.7282264128946,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.492108948060444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:45ec16f47504b5f5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 194,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.2860185393665,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.481794861921347,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 173,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.7623936685657,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.426880670928522,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 362,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 252,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 362,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.5382030918151,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.374820319063318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:inception-mercury-2-5-preview:f07bc2e66f8341c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 171,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 231,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.390731050095,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.16135373748405,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 295,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T05:52:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 294,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.1910111845057,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.825149399872654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 615,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 210,
      "draws": 458,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 605,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.018220570183,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.810416612074924,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:stepfun-step-3-7-flash:dfa24619f0407197",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 192,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.6781418918763,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.707558680335882,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 207,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.9715983344856,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.67629837390061,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:tencent-hy4-preview:b8e7119f660161ad",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 175,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.2654462588032,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.37914805089505,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 439,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 305,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 435,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.9772585746641,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.209086808065273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-2:184634950256ca6a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 150,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.873318938495,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.186100153568855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 412,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 154,
      "draws": 297,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 412,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.1906957609772,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.142561888673264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 170,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 211,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.1114181328019,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.577922253499185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-max-0902:5961da4fe746e1db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 81,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.798694413226,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.575926558583998,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.465763037423269,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 175,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.8785480714125,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.531176212156833,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.7803501103617,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.483548530056492,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 164,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.2297377289594,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.41547033342719,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "draws": 173,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.1308032078118,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.308603127079742,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.839285714285717,
      "unilateral_faults": null,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-5-flash:a0af36e4d0bc99b5",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 106,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.2455001785772,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Low (historical request variant 1)",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.284282852755524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 194,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T06:12:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.5652326310567,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.267449298158713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 148,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T03:43:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.0070834621893,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.266226481322114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 221,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.8613262957322,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.237152166315024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 783,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 255,
      "draws": 577,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 147,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 783,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.3135378586849,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.041578305308295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 456,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 162,
      "draws": 187,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 153,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 456,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.1064001968423,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.978871709726342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 159,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.0490320389179,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.91085216964937,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.834993123162105,
      "unilateral_faults": null,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:e037862ab5c7ecb3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 193,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T05:08:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.6582430520918,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.908866749062488,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 400,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 144,
      "draws": 261,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-09-25T15:34:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 400,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.172803433442,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.868918707601434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:x-ai-grok-4-7:7805d7703d63f406",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2411256233731,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.846953534414173,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 280,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-flash:14b865d3f352c468",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 198,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 280,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.136224698599,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.768091551764346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 295,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 171,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 295,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.3415254636288,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.740585261422419,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-6-luna:dfbe27d870893a52",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.4460367748802,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.335284250370272,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 751,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 240,
      "draws": 418,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 221,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 705,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.459024040264,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.298717008537093,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 46,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:meta-muse-glimmer-30b:a614a905445f79d1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 204,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T13:55:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.2969571565277,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.298673684741303,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 153,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.365696951213,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.135889350399117,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 154,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.5988635252065,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.08141203859531,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:2447db730c8d12fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 173,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0389380006973,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.045013366680111,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-5-flash:188028ef432c73f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 137,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-09-25T06:00:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.4930188095987,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.041311096948304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 713,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 227,
      "draws": 460,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 169,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 711,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.0892976785772,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.956475308723242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-terra:bd3aacb7be18fc49",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 175,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T05:45:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0809876221997,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.953275323875648,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:openai-gpt-oss-120b:7e4ecfa424847773",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 158,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.6481745285778,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.904812286411738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-terra:4506b3e0a8fb5629",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 172,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T04:29:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.8981458755488,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.870289650425716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c11fecb63644464d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 194,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.3731814594128,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.507335399739189,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:inception-mercury-2-5-preview:ff9c957a999941a2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.2283406234515,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.494975929834537,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 175,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.6914723964546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.419894829106827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 310,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 178,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 310,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.5004246962953,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.189855510586924,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 322,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d0b5b92265541548",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 167,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-09-23T05:49:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 322,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.2924084625038,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.07171218097534,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:meta-muse-spark-1-3:22ddc49b675eb171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 155,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T04:07:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.0738254576515,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.707425405221867,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 200,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-24T19:26:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 277,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.687398706827,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.567734790878136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:78fb6a9e00356b09",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 166,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.2823151197556,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.524183164803983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-5-flash:e1e7937be001cd2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 165,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T02:29:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.19072361698,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Minimal (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.372676349284893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 156,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.3822018342894,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.307756675211982,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 412,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 155,
      "draws": 312,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 412,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.6288088118372,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.276008866533179,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-terra:ac05ef4b9a51340d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 147,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-09-25T06:30:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.179558951564,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.179346281696866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 136,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 209,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.7204330427496,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.178420752709116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 296,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-flash:e0a2978fff9e81b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 129,
      "draws": 162,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.714716134723,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.08582389461898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:mistralai-mistral-medium-3-5:8de2e9417bacc9d3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 184,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T05:08:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.2686820058884,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.027941933509863,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-flash:e1a2822fb5bba20e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 185,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.9387944129749,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.978147131546923,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 161,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.301181523511,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.918261292629804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 217,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.2999660185344,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.66110569393519,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 437,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 245,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 138,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 437,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.22162299903,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.573294252110319,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:d1c3d52890a12a42",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T13:06:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.8959541468055,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.331930401575923,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 294,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:x-ai-grok-4-6:aedb1b245d3cd53f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 194,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 294,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.529445312924,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.14033355812917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-6-sol:a790476a054b6a1d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.9916701005964,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.969256362592526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "draws": 307,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T15:34:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 402,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.1586600442279,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.520265373967671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.249642583151164,
      "unilateral_faults": null,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:mistralai-mistral-medium-3-5:e327e1c801399a5f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 117,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-09-25T15:34:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 231,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.8619413155873,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.439966470700094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 184,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-23T17:36:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.9968696972862,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.384109348575187,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:130c334db8df04f4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.931015786824,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.271801424400126,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 185,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 82,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.7896230760327,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.007260933312008,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 165,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.9282390844303,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.785004751134416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 146,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 235,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.5002555098133,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.664384932466085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 142,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.336406690038,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.462135374510762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 161,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.1798500513266,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.447569003901352,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 164,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.4656687451038,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.320747401269687,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 458,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 165,
      "draws": 299,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 456,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.5497321724583,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.310346249205763,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-fable-5:346aadd5d76b812b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 189,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 304,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.971331282551,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.302860861924804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 129,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.516912386562,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.026592849743277,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:tencent-hy4-preview:014a9ceb67d5b786",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 140,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.4433122904995,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.957083818816807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 168,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 223,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.5828599891702,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.818228255319736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 172,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.7572226694713,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.720348794092118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 364,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 279,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T12:48:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.504166709032,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.623581070029456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 367,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 126,
      "max_score": null,
      "measured_at": "2026-09-25T05:23:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 367,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.7459540811358,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.220151455961185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 378,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 241,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 378,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.1888608397242,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.182072363962202,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 180,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.834382821887,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.861174993521987,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d3192451477fbf98",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.967405873055,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.629972723433358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 332,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 261,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 332,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.4511988255103,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.957773475504234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 603,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 205,
      "draws": 415,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T15:33:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 603,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.366983327068,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.58639288876681,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 436,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 154,
      "draws": 286,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 113,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 436,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.6693553431846,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Medium (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.06835881817407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 162,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.6441886130692,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.9862813021302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 384,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 238,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 384,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.6162527706854,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.704785781203059,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:c69120230888411c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 164,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.2351489145487,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.506552449736231,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:openai-gpt-oss-120b:59563b7e90e4a253",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 96,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.7129756772986,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 5.952533319730318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-max-0902:1a5946a1ae31cc68",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T05:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.2341818563582,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 2.3421974844057343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 158,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.7909588152809,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-6-astra:af89b97f9d676a8c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 2305.8243911075265,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 99.99999999999999,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 236
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-6-astra:8883275fa81b106a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T01:55:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 2248.649683482002,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 96.36396331063021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 220
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-3:650c1432bdd4728a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 2194.1105298945445,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 92.95824569345824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 218
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-fable-5-1:d307977c9774b8cb",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-intensive",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 2169.720549071415,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 91.37112263611337,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 208
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 138,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 2156.975351125996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 90.34746663281791,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 316
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 243,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 243,
      "rating_method": "sequential_elo",
      "raw_elo": 2148.940389501246,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 90.1443955387162,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 225
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-fable-5-1:fdf38228456af115",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 2124.9151167812875,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 88.63477864319661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 229
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 406,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 164,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 406,
      "rating_method": "sequential_elo",
      "raw_elo": 2118.6704565869495,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 88.08721167316827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 375
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-6-astra:9acce95ba71bd7c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 2081.47250029206,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.8365396088125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 211
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-fable-5-1:2ceef8038de90922",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T07:02:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 2079.132350592878,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.69649309071661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 207
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-5-5:12d35a0c8ebcfc9f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 2069.1372139350938,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 83.89765057926846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 704,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 236,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 704,
      "rating_method": "sequential_elo",
      "raw_elo": 2025.4729516225789,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 82.64092472785092,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 594
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 410,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 170,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 410,
      "rating_method": "sequential_elo",
      "raw_elo": 2024.0282553062893,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 82.13477554310234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 363
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:x-ai-grok-4-7:f32f0106ab05aad6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 2028.0093303656413,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.37689077370601,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 324,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 118,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1999.13038791591,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 80.92593525080028,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 290
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:x-ai-grok-4-6:d94ddefd8b9f53eb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T12:48:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1993.0294584176775,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 80.29583807622168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-5-5:e7d2796533ceda7c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1979.0551477968836,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 78.29416493729859,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:x-ai-grok-4-6:bca3abc3bf41095f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1957.513704268975,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 78.05231532268954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 187
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-6-sol:a64b94562f86a4f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T05:16:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1952.0875485730328,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.69079262608564,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-max-0902:3772000f789711bc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1951.080125087102,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.38881018245638,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-6-sol:410ceff1171c2cf1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-09-25T05:23:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1931.5983388188122,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.30573119224167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1904.2282775886874,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.92326063693565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 239
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-3-flash:1540ade2fda6b881",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T15:41:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1889.6822090150788,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 73.82177341477453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:b85a8fb56d024434",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1892.434782069571,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.7338376601718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1877.3036719014776,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.713931668433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 85,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1848.2714359945248,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.44710951598115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 249
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-5-5:7dce3bfc0734dff8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1853.5470877597693,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.45502164921955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d0b5b92265541548",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1828.4690903656574,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.9800600901681,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 360,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T01:36:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 360,
      "rating_method": "sequential_elo",
      "raw_elo": 1820.6789072396662,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.76004691232554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 267
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T04:44:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1825.7911435000174,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.49263343872869,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-3:2dbca3140c06e14c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 98,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1814.0769167802891,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.04748335935413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 142
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-6-sol:a790476a054b6a1d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1799.3800322438697,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.0440325823212,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-fable-5:1f4ca1763387a608",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.9643555457678,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.74309410747507,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 156
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-5-flash:79befaaad7974375",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 98,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.5179187609167,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.70860889776725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1778.3379873195004,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.56758096324789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1771.050242288496,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.53681950526628,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 218
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 820,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 279,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 246,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 820,
      "rating_method": "sequential_elo",
      "raw_elo": 1762.7376902370997,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.19105183427483,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 574
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-fable-5:346aadd5d76b812b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1766.2684251914866,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.07585031971833,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 158
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-8-flash:e50b23a03b02a00c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 97,
      "max_score": null,
      "measured_at": "2026-09-25T05:01:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1729.7591306402276,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.744543854931486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-flash:98dfb2fac355b676",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 82,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1725.532483239105,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.47838487808565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1727.6211599463707,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.4401888214157,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:b4ca94f8b60a9e88",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1721.8939183081075,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.23579274922259,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 97,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1710.8512444146102,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.54041731185943,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T14:04:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1703.8573282748,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.8142594407856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-5-flash:188028ef432c73f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 141,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1684.2097414809214,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.06832955325717,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 190,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-25T05:48:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.6221882023112,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.499000328638054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-max-0902:1a5946a1ae31cc68",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T05:11:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1677.695635179499,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.317058041724536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 493,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 159,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 199,
      "max_score": null,
      "measured_at": "2026-09-25T15:55:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 493,
      "rating_method": "sequential_elo",
      "raw_elo": 1650.0349636228016,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.20674314072263,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 294
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-3-flashx:43f4326da261c154",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1669.4459210255652,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.763634521125965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 788,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 341,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 345,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 788,
      "rating_method": "sequential_elo",
      "raw_elo": 1646.2595980746028,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.54346412601527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 443
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-terra:ac05ef4b9a51340d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 125,
      "max_score": null,
      "measured_at": "2026-09-25T05:01:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1643.4520137846655,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.44890987380218,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:78fb6a9e00356b09",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 155,
      "max_score": null,
      "measured_at": "2026-09-25T12:53:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1637.5421322613147,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.16040418419862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-27b:739c4d774075dc83",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T05:41:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 328,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.441721343999,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.969406483876845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 196
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-2:4571486d5f3c5826",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 151,
      "max_score": null,
      "measured_at": "2026-09-25T12:48:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.4387673937842,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.376435269561775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:tencent-hy4-preview:2077a0aa15ce66b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T14:16:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1626.6083808764358,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.22864455350476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:mistralai-mistral-medium-3-5:8de2e9417bacc9d3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.6007828704835,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.99034820792066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 410,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 195,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 410,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.431668197681,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.41476958488925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 215
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-3-flash:6bc93e3f26e0f0e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 171,
      "max_score": null,
      "measured_at": "2026-09-25T15:42:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.9190358488256,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.90420106515226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.7502453944767,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.62022193946525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 121
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:3fe477f1e3ed7e39",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.6238144120402,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.34370347170291,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:meta-muse-spark-1-3:111be2eb4c7d6522",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.9576519998002,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.832172172826105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:openai-gpt-oss-120b:7e4ecfa424847773",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1587.9165865736045,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.825621514346786,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 324,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:c69120230888411c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 163,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.3429566189945,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.55419811458228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-2:20c65e2b7513d4b4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T06:08:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.0018170020317,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.502993109011314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c37d073d6b142a09",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 153,
      "max_score": null,
      "measured_at": "2026-09-25T12:27:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.5191377924639,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.4262704810341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 148,
      "max_score": null,
      "measured_at": "2026-09-25T14:04:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 328,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.948185472631,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.4119151014792,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 338,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 160,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 338,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.4806021783322,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.21419120539835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 178
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 474,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 146,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 213,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 474,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.9996058964011,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.57759582487964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 261
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-flash:14b865d3f352c468",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 148,
      "max_score": null,
      "measured_at": "2026-09-25T05:03:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.5454713006668,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.29443897733345,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 436,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 144,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 191,
      "max_score": null,
      "measured_at": "2026-09-23T13:14:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 436,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.550717864032,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.18526830022632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 245
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-fable-5:9411c67711dccbe8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 137,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.2188092504707,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.95569071867738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.5204169498527,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.42649291219306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 286,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-3:9e30a36ab00bd740",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 127,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.5939742462938,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.33934475189269,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 159
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:tencent-hy4-preview:014a9ceb67d5b786",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 150,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.0068505036463,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.05961783013132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 166
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1595,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 511,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 744,
      "max_score": null,
      "measured_at": "2026-09-25T15:42:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 1595,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.2139081889095,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.03780039623947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 851
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T06:00:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.7377882000017,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.93262612726081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 903,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 291,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 420,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 903,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.9083210515219,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.905912358610884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 483
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 180,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T06:23:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.422857529501,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.8801788071995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 107
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-6-luna:06fb6314cedafbae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T05:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.7608692446993,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.82887430033942,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 828,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 357,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 391,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 828,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.1538799153157,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.393316198139864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 437
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:9b3aa3914934b08c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.4622565590478,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.210868821751404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-8-flash:83795e08736dcbd6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 156,
      "max_score": null,
      "measured_at": "2026-09-23T19:09:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.481048378976,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.14934593047246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.6673413728931,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.969829451519225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 364,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 151,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 172,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.2309004207027,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.87046979939683,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 192
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 404,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 176,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 404,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.3744994196975,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.86049443053713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 228
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 399,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 130,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 204,
      "max_score": null,
      "measured_at": "2026-09-25T03:31:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 399,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.0032310977772,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.325543397766175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemma-4-31b-it:8d94257f5348b920",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.0078875378504,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.26394857772395,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:x-ai-grok-4-6:aedb1b245d3cd53f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 149,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.4136462064191,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.202255327441996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.9103472929748,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.94772634864385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.5771126687582,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.905945871384226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 414,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 146,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 206,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 414,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.9507083566857,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.90440468938342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 208
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:d1c3d52890a12a42",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.6932663496493,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.89140451614368,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 129,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 196,
      "max_score": null,
      "measured_at": "2026-09-25T03:35:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.5866413784245,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.82748733223222,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 184
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-flash:04d7da5a4f2e2af2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 107,
      "max_score": null,
      "measured_at": "2026-09-25T05:32:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.4080298081694,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.77498312108857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:2447db730c8d12fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T03:31:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.392215434343,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.641747320730154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:tencent-hy4-preview:b8e7119f660161ad",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 167,
      "max_score": null,
      "measured_at": "2026-09-25T05:03:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 328,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.652345603618,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.5444682336586,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-terra:bd3aacb7be18fc49",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 136,
      "max_score": null,
      "measured_at": "2026-09-25T05:25:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.726477915025,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.40159472806108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 182
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-6-luna:3dfecd4fa4d78509",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T13:28:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.543125364701,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.2610359164719,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-3-flashx:746a19cef7ee23ef",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.7087197710289,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.17104342624617,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T03:41:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.7349393810994,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.045069424600065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 790,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 337,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 412,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 790,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.0060953819218,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.95613725220298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 378
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.6920140889088,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.748765419591805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.667361089076305,
      "unilateral_faults": null,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-8-flash:6b8b02f1f727feff",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 122,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.1599487804237,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.69228506640679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 112
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 92,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.6265842785156,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.57592667595412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 414,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 153,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 198,
      "max_score": null,
      "measured_at": "2026-09-25T12:48:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 414,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.8605390108578,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.43969869217212,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 216
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:stepfun-step-3-7-flash:dfa24619f0407197",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 117,
      "max_score": null,
      "measured_at": "2026-09-25T12:53:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.23979240712,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.401795904394994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-27b:47ad2584aeb815bb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3666111185962,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.37752224301888,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 146
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T05:00:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.663742536622,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.23196258690973,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 190,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-09-25T06:31:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.0388634204105,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.127369719800235,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-6-luna:dfbe27d870893a52",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.0240754278334,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.74933846094135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 418,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 162,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 193,
      "max_score": null,
      "measured_at": "2026-09-25T12:49:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 418,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.02865773044,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.950499952815655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 225
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d3192451477fbf98",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 116,
      "max_score": null,
      "measured_at": "2026-09-25T05:32:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.8185414839636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.51115385299343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 152
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 450,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 143,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 215,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 450,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.3770803514549,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.26630148184913,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 235
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 384,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 161,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 205,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 384,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.5613520325217,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.26386677426362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 474,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 145,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 231,
      "max_score": null,
      "measured_at": "2026-09-25T06:00:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 474,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.3386272901982,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.23126106901278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 243
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5:707323710fb901e4",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T15:55:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.1946489205093,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.01346355780045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": null,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-pro:42034002bcfc5f74",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 164,
      "max_score": null,
      "measured_at": "2026-09-25T03:31:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.8810886057918,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.91113335979322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:meta-muse-glimmer-30b:085624a1bd2a3883",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 177,
      "max_score": null,
      "measured_at": "2026-09-25T03:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.8861380916906,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.37253694835636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.6788643844177,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.34870655763811,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.7681750856045,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.55040400948236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-max-0902:5961da4fe746e1db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.8335327503344,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.26930512569967,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:meta-muse-spark-1-3:22ddc49b675eb171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 129,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 162,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.4470525560284,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.108249106768326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 133,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 179,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.1819943597798,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.507797739694716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.236482821177,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.50033505424671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.5900684076817,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.42220503142851,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 313,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 154,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 313,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.740228490143,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.275479635114195,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 159
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-3-flash:22cd36959459fbdd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 125,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.8716949943114,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.264060881669415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T03:41:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.0131556037793,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.223683029145114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:x-ai-grok-4-7:7805d7703d63f406",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.565203529387,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.42296831994141,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 281,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 156,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 281,
      "rating_method": "sequential_elo",
      "raw_elo": 1352.9565811557159,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.13255458513899,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c11fecb63644464d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.5318824887702,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.55572744176421,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 388,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 233,
      "max_score": null,
      "measured_at": "2026-09-25T15:41:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 384,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.2550007761117,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.91922843039871,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 151
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 825,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 260,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 543,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 825,
      "rating_method": "sequential_elo",
      "raw_elo": 1325.7183885846332,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.67815533375288,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 282
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:inception-mercury-2-5-preview:df3dbf369397b893",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1326.0360262339282,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.37213841472128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.6083175984572,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.134244776166305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 828,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 260,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 503,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 828,
      "rating_method": "sequential_elo",
      "raw_elo": 1297.5060696205567,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.90268984079009,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 325
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 372,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 160,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 217,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1306.8643133669477,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.88732222284614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 155
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-3-flashx:d5d0648c410f1ae2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.9295466118283,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.723346411404776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:091b7e3f3afd6616",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-25T05:13:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.7719737993527,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.46449004717655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 143,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1271.5826941372475,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.79835154781813,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:130c334db8df04f4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1274.647621010709,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.969178885975495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 127,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1258.620863230517,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.9241439224965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 138,
      "max_score": null,
      "measured_at": "2026-09-25T07:32:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1256.4377579120328,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.89005402357793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:f9ec308f9bb8850b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1255.5273945881124,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.81799644348555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1242.1001290144154,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Medium (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.933850968190974,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 310,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 213,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 310,
      "rating_method": "sequential_elo",
      "raw_elo": 1236.6531644054721,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.88038109999295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 221,
      "max_score": null,
      "measured_at": "2026-09-25T04:02:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1211.2843177396303,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.300886532170168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 158,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 259,
      "max_score": null,
      "measured_at": "2026-09-25T01:46:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1214.094123317484,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.100848093492324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 135,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1177.1039837496114,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.773211795209818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 135,
      "max_score": null,
      "measured_at": "2026-09-25T12:48:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1173.139299796228,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.566789813099383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-flash:e1a2822fb5bba20e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 196,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1165.0488835259146,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.222283900175665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-2:184634950256ca6a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 183,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1148.205706929032,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.088852302816452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 382,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 155,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 265,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 382,
      "rating_method": "sequential_elo",
      "raw_elo": 1124.5456396534069,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.430360770406754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:mistralai-mistral-medium-3-5:e327e1c801399a5f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 191,
      "max_score": null,
      "measured_at": "2026-09-25T14:16:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1119.0368805636974,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.23037696584976,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 750,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 237,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 568,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 750,
      "rating_method": "sequential_elo",
      "raw_elo": 1109.881419184016,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.026580421066036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 182
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 183,
      "max_score": null,
      "measured_at": "2026-09-25T02:18:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1099.7712464212616,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.117792770251928,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 754,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 229,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 599,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 754,
      "rating_method": "sequential_elo",
      "raw_elo": 1092.2996731742678,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.922871015070534,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 155
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 144,
      "max_score": null,
      "measured_at": "2026-09-25T05:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1091.2531945362703,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.38472503344923,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 171,
      "max_score": null,
      "measured_at": "2026-09-23T03:27:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1086.0713160839841,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.21045764633968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:openai-gpt-oss-120b:59563b7e90e4a253",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 199,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1080.1171427813263,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.848650743910238,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:inception-mercury-2-5-preview:f07bc2e66f8341c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 211,
      "max_score": null,
      "measured_at": "2026-09-25T04:36:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1077.15087262024,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.711376551122164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-5-flash:a0af36e4d0bc99b5",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1089.5177128267528,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Low (historical request variant 1)",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.694481540791458,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": null,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 140,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1070.9035033771586,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.019261559659135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 768,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 245,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 623,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 768,
      "rating_method": "sequential_elo",
      "raw_elo": 1059.0605185213187,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.841650392139822,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 356,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 143,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 265,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 356,
      "rating_method": "sequential_elo",
      "raw_elo": 1068.5338826129823,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.839172745237917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:openai-gpt-oss-120b:07d17099885c6bdb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 179,
      "max_score": null,
      "measured_at": "2026-09-25T05:13:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1058.036358089146,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.396389762012983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:e037862ab5c7ecb3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 186,
      "max_score": null,
      "measured_at": "2026-09-25T13:28:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1047.1995225663443,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.721197658478708,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 162,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1047.7461247257522,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.687011705599502,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:meta-muse-glimmer-30b:20d2aea9e268d0ef",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 177,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1040.810738244802,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.281804865949653,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-5-flash:e1e7937be001cd2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 196,
      "max_score": null,
      "measured_at": "2026-09-25T03:46:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1008.5726541014125,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Minimal (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.316773056875327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 205,
      "max_score": null,
      "measured_at": "2026-09-25T05:48:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1001.7884429744031,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.86158687607802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 164,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 996.4721889908689,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.441769674969127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 418,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 158,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 327,
      "max_score": null,
      "measured_at": "2026-09-25T07:49:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 414,
      "rating_method": "sequential_elo",
      "raw_elo": 989.1863512819759,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.978770000497704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 4,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 166,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 983.6847562803387,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.636523889428613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 155,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 958.6120200971899,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.9868688465287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 151,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 334,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 945.0674090073451,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.160401525981356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 143,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 945.7882412819017,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.077395343984001,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 818,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 258,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 714,
      "max_score": null,
      "measured_at": "2026-09-25T04:49:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 818,
      "rating_method": "sequential_elo",
      "raw_elo": 931.6901172244059,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.859889298232568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 222,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 829.0826803647128,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.993147556840411,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:meta-muse-glimmer-30b:a614a905445f79d1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 213,
      "max_score": null,
      "measured_at": "2026-09-25T01:29:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 818.5249709768012,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.328311136424571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 248,
      "max_score": null,
      "measured_at": "2026-09-25T05:52:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 716.9732845937543,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-fable-5-1:d307977c9774b8cb",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-intensive",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-09-25T03:43:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 2318.897092303519,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 229
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-3:2dbca3140c06e14c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-09-25T05:06:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 2174.6692101629533,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 91.34449020371359,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 230
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-3:650c1432bdd4728a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 2165.3489889633206,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 90.7636514969772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 219
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 218,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 2126.4040981564867,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 88.30380211671529,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-5-5:12d35a0c8ebcfc9f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-09-25T12:27:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 2102.4016317134924,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.98139509310396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-6-astra:9acce95ba71bd7c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T05:13:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 2070.4006161095167,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.03489742391993,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 210
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 762,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 261,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 128,
      "max_score": null,
      "measured_at": "2026-09-25T15:24:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 762,
      "rating_method": "sequential_elo",
      "raw_elo": 2054.014996548248,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 84.32762532825016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 605
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-fable-5:9411c67711dccbe8",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 2056.7934715850724,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 84.1691849172907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 193
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-6-astra:af89b97f9d676a8c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T06:05:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 2044.7653544019536,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 83.44269781880206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-8-flash:e50b23a03b02a00c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 2039.456503193102,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 83.10880420461697,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 178
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-6-sol:410ceff1171c2cf1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 2034.2953622376588,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.84045926750574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-fable-5-1:2ceef8038de90922",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T06:44:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 2016.1486653040506,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.7142763946855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 193
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:b4ca94f8b60a9e88",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 2014.87542955774,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.68122776333043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 183
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 327,
      "rating_method": "sequential_elo",
      "raw_elo": 2003.9172974884755,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.2042772769244,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 236
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 328,
      "rating_method": "sequential_elo",
      "raw_elo": 1997.7574443097017,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 80.83425675693161,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 266
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-flash:e0a2978fff9e81b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T03:13:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1985.940688516747,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 79.88316261692358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1968.2185266674333,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 78.62474263949787,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:meta-muse-spark-1-3:111be2eb4c7d6522",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-24T23:38:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1958.2333885274027,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 78.27779768942712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 180,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T14:10:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1960.5769388316662,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 78.12478117978807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 151
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:tencent-hy4-preview:2077a0aa15ce66b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-09-25T00:49:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1951.562346562994,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.83883887689821,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 175
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-5-5:7dce3bfc0734dff8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-09-25T12:27:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1959.1974935170713,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.35850943307017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 786,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 256,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 786,
      "rating_method": "sequential_elo",
      "raw_elo": 1933.1562045476744,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.04707674780836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 611
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:meta-muse-spark-1-3:4bb11a89323f5400",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1938.01034564622,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.02031061725003,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 186
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-terra:bd3aacb7be18fc49",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1936.8206165711558,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.93585154551911,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 173
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-6-luna:06fb6314cedafbae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1946.831431122891,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.68636345470857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-fable-5-1:fdf38228456af115",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1928.728046457806,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.44706783220323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 177
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-2:4571486d5f3c5826",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T04:55:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1926.5484896384157,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.36982205482883,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 207
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:7f6340c5cd60d7e7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1932.532829336563,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.77367546807812,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T05:26:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1919.2834556174316,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.74725395578018,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 173
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-pro:42034002bcfc5f74",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1908.5199707434276,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.28091626993594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:b85a8fb56d024434",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-09-25T07:31:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1923.7890812127462,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.19336305189155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 330,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 330,
      "rating_method": "sequential_elo",
      "raw_elo": 1900.1607633818742,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.94353809455754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 250
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-fable-5:1f4ca1763387a608",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1903.2394730829708,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.90758169037487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 174
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:x-ai-grok-4-6:bca3abc3bf41095f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1897.9680555231073,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.56969734908822,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-flash:98dfb2fac355b676",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1887.0566314718924,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.00144873524822,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-3-flash:6bc93e3f26e0f0e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1887.5237166831148,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 73.9709651519967,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 336,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-25T03:04:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 336,
      "rating_method": "sequential_elo",
      "raw_elo": 1881.963566228328,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 73.85631875502746,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 249
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-6-astra:8883275fa81b106a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T03:45:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1875.2559958586826,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 73.19124617557102,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-max-0902:3772000f789711bc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1885.8535702985014,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.87471300160755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:d1c3d52890a12a42",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1870.302600353424,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.98934050814864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-max-0902:1a5946a1ae31cc68",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T07:31:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1865.4579020509198,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.7714779302936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-3-flashx:43f4326da261c154",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1864.6192415868886,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.74427757233467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-24T21:34:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1849.9042563122262,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.62538316070135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-8-flash:6b8b02f1f727feff",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-09-25T03:04:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1848.7427852132082,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.62237123829571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 173
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:x-ai-grok-4-7:7805d7703d63f406",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T12:47:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1860.3173121974187,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.24448433375413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-24T21:34:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1842.489180451281,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.170312983184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1838.5649567775201,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.82103497731079,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-5-flash:79befaaad7974375",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1834.450451701581,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.75278873396961,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-fable-5:346aadd5d76b812b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T05:00:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1834.422702351709,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.71820370255907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-5-flash:188028ef432c73f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.5502813354785,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.73203415149305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 159
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-6-sol:a64b94562f86a4f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1829.9362462808288,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.64945689149215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-8-flash:83795e08736dcbd6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1798.6291417013492,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.57629933967782,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-5-5:e7d2796533ceda7c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1813.795133998968,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.40320390202572,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-09-25T01:18:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1793.4876526516734,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.29746038794151,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 870,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 343,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 276,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 870,
      "rating_method": "sequential_elo",
      "raw_elo": 1772.4484196222327,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.13193639618068,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 501
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-6-sol:a790476a054b6a1d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1725.945749179493,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.21642923019296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 336,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 119,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 336,
      "rating_method": "sequential_elo",
      "raw_elo": 1705.2403347677614,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.18239982783971,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:x-ai-grok-4-6:d94ddefd8b9f53eb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-09-25T06:11:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1706.161778721584,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.03521018257703,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:tencent-hy4-preview:014a9ceb67d5b786",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 141,
      "max_score": null,
      "measured_at": "2026-09-25T14:36:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.9656968929207,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.58021342324713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 193
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d0b5b92265541548",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-09-25T13:25:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.2933466880772,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.08933985378316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 194
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:3fe477f1e3ed7e39",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.5720186416438,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.94960636853664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:f9ec308f9bb8850b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1626.900963741159,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.38797062519658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 348,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-27b:47ad2584aeb815bb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 145,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 151,
      "max_score": null,
      "measured_at": "2026-09-25T00:36:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 348,
      "rating_method": "sequential_elo",
      "raw_elo": 1618.1605396285938,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.945684696607124,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 480,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 196,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 480,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.2310136332721,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.899996001122055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 249
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 478,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 169,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 174,
      "max_score": null,
      "measured_at": "2026-09-25T01:00:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 478,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.5154003824932,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.82115624580523,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 286
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-3-flashx:746a19cef7ee23ef",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.1284190954095,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.68992736691443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:45ec16f47504b5f5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 138,
      "max_score": null,
      "measured_at": "2026-09-25T06:04:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.531598919758,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.44640162344343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 433,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 143,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 173,
      "max_score": null,
      "measured_at": "2026-09-25T04:49:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 433,
      "rating_method": "sequential_elo",
      "raw_elo": 1603.9204548597472,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.21913279521076,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 249
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 336,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-flash:e1a2822fb5bba20e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 140,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 336,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.2344503904574,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.77974293719396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 186
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.9709274369272,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.7454811145915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 128
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 296,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-5-flash:e1e7937be001cd2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 131,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.7439848145218,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Minimal (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.54349612359615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 157
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 336,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-flash:04d7da5a4f2e2af2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 137,
      "max_score": null,
      "measured_at": "2026-09-25T07:15:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 336,
      "rating_method": "sequential_elo",
      "raw_elo": 1587.5047468720559,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.07127974669768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 412,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 162,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 411,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.0758348930235,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.929576936759275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 232
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 386,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 142,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 386,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.0957059667985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.56765629222236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 213
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 492,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 157,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 204,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.7774959551684,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.86613972193045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 245
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 339,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 152,
      "max_score": null,
      "measured_at": "2026-09-25T12:47:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 339,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.1089106507507,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.72441106072859,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 158
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T07:48:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1568.3989131462947,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.629833111248594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 128
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 934,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 298,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 410,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 934,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.267097460467,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.50461528693461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 513
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-max-0902:5961da4fe746e1db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.059466017882,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.31161562786239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 494,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 147,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 226,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 494,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.1150032151852,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.98273918474334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 253
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:9b3aa3914934b08c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.6492842445664,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.11187823957251,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 166,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.2308172983269,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.611716687770866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-3:9e30a36ab00bd740",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 162,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.2354984855863,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.263519135398994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 152
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 162,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.9072035200847,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.92778094014556,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 486,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 149,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 225,
      "max_score": null,
      "measured_at": "2026-09-25T05:41:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.8009322240273,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.814135198615915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 238
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 96,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.290841930129,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.28851664089777,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-3-flashx:d5d0648c410f1ae2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.5273787833557,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.11749746309352,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.6696003044897,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.9350548600679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 124
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:091b7e3f3afd6616",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.1032066491546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.486251574367515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 119,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.5775244954111,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.979799568566214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.134219983223996,
      "unilateral_faults": null,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-09-25T05:06:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.4237574789388,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.543105104646564,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-flash:14b865d3f352c468",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 164,
      "max_score": null,
      "measured_at": "2026-09-25T03:20:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.0879424040954,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.266186543558746,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.3995689204392,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.838972097614196,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 124
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 272,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:meta-muse-spark-1-3:22ddc49b675eb171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 131,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.2174451164249,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.149913347085835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 348,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 184,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 348,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.6403620647127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.921635612672766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 158
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 330,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c37d073d6b142a09",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 169,
      "max_score": null,
      "measured_at": "2026-09-25T05:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 330,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.9149423027568,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.903521988412955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 156
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 488,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 148,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 230,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 488,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.5641181916208,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.87613336669571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 214
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 506,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 154,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 228,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 506,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.885554594425,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.85471815151569,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 237
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 489,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 151,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 247,
      "max_score": null,
      "measured_at": "2026-09-25T04:55:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 489,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.8370706263297,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.531340418862875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 416,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 154,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 208,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 416,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.8040752135607,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.37217573314729,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 340,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 169,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 340,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.5099746623619,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.992692305851016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:tencent-hy4-preview:b8e7119f660161ad",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.4170921444886,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.71005822548814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-2:20c65e2b7513d4b4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 117,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.476853557659,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.628065333452454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 820,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 253,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 429,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 820,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.2480292126502,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.48522862689852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 356
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1767,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 534,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 932,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 1767,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.7523429759424,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.38071106501111,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 801
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-09-25T02:56:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.4483679946977,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.27096420079218,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 152,
      "max_score": null,
      "measured_at": "2026-09-25T12:47:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.2944605339005,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.187462067298945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 338,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-terra:ac05ef4b9a51340d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 139,
      "draws": 28,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 193,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 338,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.4045000243977,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.59328944547627,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 410,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 145,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 202,
      "max_score": null,
      "measured_at": "2026-09-25T06:44:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 410,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.9554782791624,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.49703925426421,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 205
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 940,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 376,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 527,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 940,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.4377306941285,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.47240899941553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 388
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:78fb6a9e00356b09",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 150,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.4439636276202,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.84626674582942,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 494,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 157,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 256,
      "max_score": null,
      "measured_at": "2026-09-25T05:00:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 494,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.9002702101798,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.52073030334479,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 206
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 150,
      "max_score": null,
      "measured_at": "2026-09-25T05:43:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.862610827383,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.09731404389463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-3-flash:22cd36959459fbdd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 183,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.963785463048,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.867686109837216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 422,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 161,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 217,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 422,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.9098744914804,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.52477509866081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 204
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 426,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 207,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 426,
      "rating_method": "sequential_elo",
      "raw_elo": 1357.2698586081942,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.31219893783358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 198
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d3192451477fbf98",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 179,
      "max_score": null,
      "measured_at": "2026-09-25T04:48:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.4627200228902,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.053752059801255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-terra:4506b3e0a8fb5629",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 137,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.2974637325274,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.861028222502206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.0757812157685,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.708782628285576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 486,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 167,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 258,
      "max_score": null,
      "measured_at": "2026-09-25T15:10:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.7431065972619,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.60041525625513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 192
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 122,
      "max_score": null,
      "measured_at": "2026-09-25T05:00:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.8761528680536,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.26936162900415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:openai-gpt-oss-120b:59563b7e90e4a253",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 151,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.558641338468,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.54712305704406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 207,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 116,
      "max_score": null,
      "measured_at": "2026-09-25T15:08:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 207,
      "rating_method": "sequential_elo",
      "raw_elo": 1290.8680313592329,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.7955878292642,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-2:184634950256ca6a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 133,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1273.2303784522567,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.87440457242257,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 215,
      "max_score": null,
      "measured_at": "2026-09-25T13:25:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 328,
      "rating_method": "sequential_elo",
      "raw_elo": 1265.2546120590778,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.59176650389889,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 125,
      "max_score": null,
      "measured_at": "2026-09-25T14:36:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.0923632699235,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.9978767970118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-6-luna:3dfecd4fa4d78509",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1239.8605732376068,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.96181958467115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 163,
      "max_score": null,
      "measured_at": "2026-09-23T20:21:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1221.4331847566114,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.73971611252159,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-27b:739c4d774075dc83",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 155,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1220.0562223930833,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.70967503312307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1200.9451326757076,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.38410669171022,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 810,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 253,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 541,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 810,
      "rating_method": "sequential_elo",
      "raw_elo": 1191.8149950533534,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.2888894086943,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 222
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 328,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 432,
      "rating_method": "sequential_elo",
      "raw_elo": 1206.8396642184798,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.0194479241334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.591247874473638,
      "unilateral_faults": null,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 171,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1200.7278853564226,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.499648290466038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.834993123162105,
      "unilateral_faults": null,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:mistralai-mistral-medium-3-5:8de2e9417bacc9d3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 157,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1176.5381220136703,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.009077920581134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 176,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1161.472768750128,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.171288882691577,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:130c334db8df04f4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1177.7559335408441,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.106273873269323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 620,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 244,
      "draws": 28,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 421,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 620,
      "rating_method": "sequential_elo",
      "raw_elo": 1156.6289503283863,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.979339503978853,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 816,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 254,
      "draws": 85,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 555,
      "max_score": null,
      "measured_at": "2026-09-25T15:10:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 816,
      "rating_method": "sequential_elo",
      "raw_elo": 1147.8027589015026,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.63511971413311,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 176
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 187,
      "max_score": null,
      "measured_at": "2026-09-24T15:30:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1150.2999734403245,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.53417748662991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 422,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 302,
      "max_score": null,
      "measured_at": "2026-09-25T15:10:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 422,
      "rating_method": "sequential_elo",
      "raw_elo": 1144.6544348969242,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.464909991973933,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 267,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 203,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 267,
      "rating_method": "sequential_elo",
      "raw_elo": 1149.403958214884,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.450673929819136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 165,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1148.1864008170126,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.3094167434742,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-5-flash:a0af36e4d0bc99b5",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T01:10:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1153.0781551966284,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Low (historical request variant 1)",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.244330749129336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-6-luna:dfbe27d870893a52",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1157.797087354043,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.928158563781658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 162,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1136.8956765035823,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.621128644913895,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 157,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1131.9050992310254,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.190333048264026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 164,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1105.2901358809513,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.7057657786473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 392,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 285,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 392,
      "rating_method": "sequential_elo",
      "raw_elo": 1098.203423189367,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.615301347660477,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 153,
      "max_score": null,
      "measured_at": "2026-09-25T03:40:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1104.1232463585047,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.566392735289362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 338,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 256,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 338,
      "rating_method": "sequential_elo",
      "raw_elo": 1093.6370561762542,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.246018169613286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:openai-gpt-oss-120b:7e4ecfa424847773",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 180,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1095.9008746850254,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.151419561181175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 166,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1094.304139623621,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.048639403495315,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:inception-mercury-2-5-preview:df3dbf369397b893",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 171,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1093.5609104681846,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.977589553967935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 152,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1089.7617560473384,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.706276161565984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:inception-mercury-2-5-preview:f07bc2e66f8341c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 188,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1081.047870568292,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.25431191745537,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:mistralai-mistral-medium-3-5:e327e1c801399a5f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 187,
      "max_score": null,
      "measured_at": "2026-09-25T06:09:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1081.280252900736,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.249093186396834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:e037862ab5c7ecb3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 191,
      "max_score": null,
      "measured_at": "2026-09-25T05:30:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1079.7568802673843,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.18259900050788,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:c69120230888411c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 181,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1079.957238668903,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.175682332360164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 213,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 161,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 213,
      "rating_method": "sequential_elo",
      "raw_elo": 1071.5827214437497,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.574609551117437,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 259,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 202,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 259,
      "rating_method": "sequential_elo",
      "raw_elo": 1068.216179133427,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.524475172908698,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:2447db730c8d12fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 195,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1068.6933279372302,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.50177018126175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 190,
      "max_score": null,
      "measured_at": "2026-09-18T18:42:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1061.3788853371843,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.059984646529276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 169,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1057.325050187689,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.775390810505247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 360,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 279,
      "max_score": null,
      "measured_at": "2026-09-25T00:02:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 360,
      "rating_method": "sequential_elo",
      "raw_elo": 1049.1009470500528,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.59669007853958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 149,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1054.246550419755,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.49982887875695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemma-4-31b-it:8d94257f5348b920",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 177,
      "max_score": null,
      "measured_at": "2026-09-25T14:10:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1049.0332225783065,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.30140252649068,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:inception-mercury-2-5-preview:ff9c957a999941a2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 195,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1046.529413953533,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.163090376598188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:x-ai-grok-4-6:aedb1b245d3cd53f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 228,
      "max_score": null,
      "measured_at": "2026-09-25T01:00:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1044.5694235124092,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.142938274891982,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:meta-muse-glimmer-30b:20d2aea9e268d0ef",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 199,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1041.1249118223438,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.879468141442242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 192,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1034.0499364772634,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.446247803353653,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:stepfun-step-3-7-flash:dfa24619f0407197",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 197,
      "max_score": null,
      "measured_at": "2026-09-25T05:03:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1023.2764363744144,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.783530804579915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 400,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 149,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 306,
      "max_score": null,
      "measured_at": "2026-09-25T15:08:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 400,
      "rating_method": "sequential_elo",
      "raw_elo": 1011.1392261105159,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.87105486279739,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-3-flash:1540ade2fda6b881",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 181,
      "max_score": null,
      "measured_at": "2026-09-25T05:13:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1008.7351772149632,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.860857984814505,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 174,
      "max_score": null,
      "measured_at": "2026-09-25T13:25:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 983.0303224250979,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.267003258236837,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 790,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 247,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 659,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 790,
      "rating_method": "sequential_elo",
      "raw_elo": 943.9992522361157,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.306065189421517,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 173,
      "max_score": null,
      "measured_at": "2026-09-25T15:24:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 942.5334712146507,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.768455567867043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 492,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 162,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 408,
      "max_score": null,
      "measured_at": "2026-09-25T15:10:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 851.2838770926161,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.38300416268924,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-6-astra:af89b97f9d676a8c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 2285.455463434802,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 99.65604153579027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 250
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-3:650c1432bdd4728a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 2254.304779047959,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 97.58127501121015,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 247
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-6-astra:8883275fa81b106a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T06:08:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 2251.6025571214686,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 97.38715231698653,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 245
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 284,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-6-astra:9acce95ba71bd7c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-23T10:05:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 2213.9870048414227,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 94.95689897734873,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 275
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-fable-5-1:d307977c9774b8cb",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-intensive",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 506,
      "rating_method": "sequential_elo",
      "raw_elo": 2181.6000531046766,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 92.69213372868536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 476
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-fable-5-1:2ceef8038de90922",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T05:08:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 2169.7960624345815,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 91.91733247569104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 242
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 2126.6926815025818,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 89.24673663502878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 312
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 2127.7356846387693,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 88.9097764968694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-5-5:12d35a0c8ebcfc9f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 2126.288409526174,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 88.05090981009354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 2077.3800463802863,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.64043148326957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 211
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-6-sol:410ceff1171c2cf1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 2043.581158442173,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 82.55615873333252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-5-5:7dce3bfc0734dff8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 2030.8784144609388,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.57822709514194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 472,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 178,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T15:14:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 472,
      "rating_method": "sequential_elo",
      "raw_elo": 2015.2147642946993,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.48022089997005,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 405
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-fable-5-1:fdf38228456af115",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1996.5610215766385,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 80.28043626941351,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 216
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-5-5:e7d2796533ceda7c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 2004.3585172896226,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 79.85364697365718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1980.0748987537597,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 79.42432262453787,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 282
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-6-sol:a64b94562f86a4f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T05:43:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1990.2209917943844,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 78.85328563520711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1925.7828444100635,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.48747960512179,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 196
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-27b:739c4d774075dc83",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-09-25T03:15:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1913.6688351436223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.90167026913919,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 233
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:3fe477f1e3ed7e39",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1915.2366881308399,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 73.64786897600108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T12:17:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1887.874488266294,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.93190187054188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 196
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-pro:42034002bcfc5f74",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 82,
      "max_score": null,
      "measured_at": "2026-09-25T04:30:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1875.5836068988096,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.21134396175917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d0b5b92265541548",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1870.6286447706118,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.8729308953561,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d3192451477fbf98",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1868.5979423021952,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.79125135121897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 200
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:tencent-hy4-preview:014a9ceb67d5b786",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T04:36:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1860.3495757977012,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.19032884996027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:x-ai-grok-4-6:d94ddefd8b9f53eb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1853.977814531143,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.75695908292762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 280,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-flash:98dfb2fac355b676",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-09-22T13:00:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 280,
      "rating_method": "sequential_elo",
      "raw_elo": 1838.4946857611073,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.77939307553763,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:x-ai-grok-4-6:bca3abc3bf41095f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1837.9987970990019,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.68601350315085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-3-flashx:43f4326da261c154",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1839.206746931014,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.6758710523356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1820.5862524640922,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.53774121733082,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 197
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T05:16:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1818.9857739328693,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.3072563481697,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 173
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-3-flash:6bc93e3f26e0f0e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T05:18:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1816.0959356058881,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.19200834208425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 175
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-3:9e30a36ab00bd740",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 96,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1812.148293499103,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.95978288951696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 166
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 370,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 370,
      "rating_method": "sequential_elo",
      "raw_elo": 1800.2013496000136,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.42033275926899,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 271
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 129,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T07:53:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.5455136114233,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.15463779430945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 264
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-3:2dbca3140c06e14c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1799.0069770627845,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.07902568340647,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 183
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-fable-5:1f4ca1763387a608",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1792.3257562370536,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.61852060343541,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1779.0511817326906,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.71581777847483,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-3-flash:1540ade2fda6b881",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T04:36:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1777.3553951311483,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.67599407739836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c37d073d6b142a09",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1774.4914466514606,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.39010876108995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:tencent-hy4-preview:2077a0aa15ce66b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 118,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 115,
      "max_score": null,
      "measured_at": "2026-09-24T19:16:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1770.265865183308,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.23965370756527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 177
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 82,
      "max_score": null,
      "measured_at": "2026-09-23T15:27:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1760.9349440620415,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 64.55194498926986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 118,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1756.5529772065865,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 64.43923630535639,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 233
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:x-ai-grok-4-7:f32f0106ab05aad6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1767.6454148188684,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 64.10825307420451,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 275,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 96,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 275,
      "rating_method": "sequential_elo",
      "raw_elo": 1741.9329256680928,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.29321035518914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-3-flash:22cd36959459fbdd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T12:54:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1740.5070985519903,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.151925655306094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:b85a8fb56d024434",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1754.6299005256376,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.97794411108242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 280,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-2:4571486d5f3c5826",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 280,
      "rating_method": "sequential_elo",
      "raw_elo": 1715.2546008597135,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.519597081386934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 174
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-8-flash:e50b23a03b02a00c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1714.4722670576302,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.419590951500844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-fable-5:9411c67711dccbe8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1712.247750873124,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.26424951289066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:x-ai-grok-4-7:08dd7ecb5fefd0b4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1719.264076773523,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.720023895279155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:d1c3d52890a12a42",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1716.5424355001617,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.51080360289881,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1696.2581746078608,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.08939481420384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 163
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 340,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-fable-5:346aadd5d76b812b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 140,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 340,
      "rating_method": "sequential_elo",
      "raw_elo": 1684.7963698508281,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.62572675932049,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 200
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 896,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 369,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 348,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 896,
      "rating_method": "sequential_elo",
      "raw_elo": 1685.8886855839849,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.59542381477149,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 548
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1687.9165793259276,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.58082426309626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 169
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:b4ca94f8b60a9e88",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1682.1774714179971,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.229693911875664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 147
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 374,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 125,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 374,
      "rating_method": "sequential_elo",
      "raw_elo": 1675.240369774397,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.05264202522787,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 228
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 133,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.705689755907,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.01956202861504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 211
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-6-sol:a790476a054b6a1d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1677.4254768113583,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.99178835476464,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1659.3017330955558,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.62738467323732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-3-flashx:746a19cef7ee23ef",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.843640585245,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.16570558834896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 377,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 146,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 163,
      "max_score": null,
      "measured_at": "2026-09-22T14:30:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 377,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.67704856788,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.00973194901733,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 214
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 874,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 286,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 343,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 874,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.2314652141795,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.66854839969095,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 531
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 364,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-8-flash:6b8b02f1f727feff",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 148,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 164,
      "max_score": null,
      "measured_at": "2026-09-25T12:49:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1627.8857977812459,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.860008031893024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 200
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1627.6300514217016,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.45085414085405,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 462,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 197,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 462,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.1437056065654,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.029289758171764,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 265
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meta-muse-spark-1-3:4bb11a89323f5400",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 136,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.257134738404,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.837866826293656,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-terra:ac05ef4b9a51340d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 122,
      "max_score": null,
      "measured_at": "2026-09-25T02:54:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.6449502469552,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.59577102591772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 144
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.2940888111907,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.55982608465452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 358,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-5-flash:79befaaad7974375",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 152,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 358,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.9642439877327,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.904620380720125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 206
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:c69120230888411c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 145,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 182,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.1810602596506,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.83609631342515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 168
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 448,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 162,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 177,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 448,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.7527432795964,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.5838024312028,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 271
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.8267718093618,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.3529522501055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.3007031258494,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.966061908297576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 152
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 478,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 151,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 201,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 478,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.2577772164589,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.304688764068835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 277
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-3-flashx:d5d0648c410f1ae2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T05:32:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.1370577997548,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.703976589404945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-5-flash:a0af36e4d0bc99b5",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.8609523193231,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Low (historical request variant 1)",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.17948017902008,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 94
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 442,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 160,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 209,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 442,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.9341990279331,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.03197838855901,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 233
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-25T15:14:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.4570672951763,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.994068196362356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 288,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:f9ec308f9bb8850b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.1985659619909,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.937997689218676,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 142
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 881,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 288,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 413,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 877,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.7165694005175,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.66524674768772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 464
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-22T19:29:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.7906560666256,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.413228051643856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meta-muse-spark-1-3:111be2eb4c7d6522",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 155,
      "max_score": null,
      "measured_at": "2026-09-25T02:54:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.883430442997,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.07302698639267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 490,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 151,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 243,
      "max_score": null,
      "measured_at": "2026-09-25T15:41:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 490,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.47687099777,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.849290405989954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 247
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 352,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:x-ai-grok-4-6:aedb1b245d3cd53f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 147,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 155,
      "max_score": null,
      "measured_at": "2026-09-25T05:19:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.0956228971488,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.74075816746098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 197
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.46710023982,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.29932137115699,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-5-flash:188028ef432c73f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 143,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 175,
      "max_score": null,
      "measured_at": "2026-09-25T06:00:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.3071353060327,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.14767678741904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 175
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 518,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 158,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 294,
      "max_score": null,
      "measured_at": "2026-09-25T15:41:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 518,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.6761238799647,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.42124939768273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 224
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:x-ai-grok-4-7:7805d7703d63f406",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T05:48:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.942734019108,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.04669634247453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 434,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 144,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 211,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 434,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.3950796409993,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.82465145654429,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 223
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T06:23:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.779451138306,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.77403884472038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-2:184634950256ca6a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 150,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 190,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.9471620478644,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.37564898729753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 346,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c11fecb63644464d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 144,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 153,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 346,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.90708301305,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.02962894499428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 193
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 498,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 151,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 245,
      "max_score": null,
      "measured_at": "2026-09-25T05:41:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 498,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.7674379150828,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.723138765545265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 253
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 766,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 251,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 361,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 766,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.9401740719447,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.52282307590832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 405
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 506,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 171,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 276,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 498,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.8511196698983,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.43267997067568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 222
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5:707323710fb901e4",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 85,
      "max_score": null,
      "measured_at": "2026-09-25T04:49:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.0583806015484,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.25132030051264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-09-25T12:17:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.3414175278592,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.021359823488645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meta-muse-glimmer-30b:085624a1bd2a3883",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 151,
      "max_score": null,
      "measured_at": "2026-09-25T14:10:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.0098804966221,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.90233392575276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 167
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 905,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 282,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 474,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 905,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.5367015067034,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.77503608244635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 431
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 175,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.8861416519917,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.59689833921164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-max-0902:5961da4fe746e1db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.8170161899664,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.58541659334441,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 274,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:tencent-hy4-preview:b8e7119f660161ad",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 145,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.8567751138708,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.508357711216625,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-6-luna:3dfecd4fa4d78509",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.3198602798677,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.43933485308878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 858,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 365,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 471,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 858,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.68078832153,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.38360964767335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 387
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1868,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 572,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1017,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 1868,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.3727009046795,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.31127094485157,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 851
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.3985733716686,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.77833026164878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 120,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.5301665145182,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.673700863833744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-terra:bd3aacb7be18fc49",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 145,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 213,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.7920865935212,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.710585867697205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-flash:14b865d3f352c468",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T05:13:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.2675846512514,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.59707450331787,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 338,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-flash:e0a2978fff9e81b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 205,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 338,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.4683915813177,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.43117903521025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:091b7e3f3afd6616",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.2346624876882,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.3468858005456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 565,
      "max_score": null,
      "measured_at": "2026-09-25T13:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 950,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.6214948670254,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.44617773407611,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.709041527651344,
      "unilateral_faults": null,
      "wins": 385
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 954,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 399,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 560,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 954,
      "rating_method": "sequential_elo",
      "raw_elo": 1358.9488067831278,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.724790002335574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 394
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 437,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 224,
      "max_score": null,
      "measured_at": "2026-09-25T06:12:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 437,
      "rating_method": "sequential_elo",
      "raw_elo": 1352.0100444121738,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.492528172236426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 213
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 160,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.9282549861598,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.20183371033238,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 132
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 412,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 210,
      "max_score": null,
      "measured_at": "2026-09-25T15:14:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 412,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.8705284872053,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.04284479501129,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meta-muse-spark-1-3:22ddc49b675eb171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 135,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1343.1757005337963,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.51558912753892,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:9b3aa3914934b08c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.4235677106053,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.40173017070555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 846,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 264,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 525,
      "max_score": null,
      "measured_at": "2026-09-25T12:53:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 846,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.7340905811943,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.04461312474943,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 321
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.291135506017,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Medium (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.84961262725807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 394,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 234,
      "max_score": null,
      "measured_at": "2026-09-25T07:40:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 394,
      "rating_method": "sequential_elo",
      "raw_elo": 1327.433947126968,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.77746607761612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 398,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 265,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 398,
      "rating_method": "sequential_elo",
      "raw_elo": 1326.6538472650284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.73196065042729,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-8-flash:83795e08736dcbd6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 152,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1327.3203385304666,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.51374807836425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 235,
      "max_score": null,
      "measured_at": "2026-09-25T15:14:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.3770693573304,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.279940763003445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-max-0902:1a5946a1ae31cc68",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1340.6210604790344,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.25966512394811,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-6-luna:06fb6314cedafbae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1340.176559634495,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.2583774058522,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:78fb6a9e00356b09",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 158,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.015355771146,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.2366026851926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 124
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meta-muse-glimmer-30b:20d2aea9e268d0ef",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 136,
      "max_score": null,
      "measured_at": "2026-09-25T13:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.882208334911,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.202863811457455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:openai-gpt-oss-120b:7e4ecfa424847773",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 148,
      "max_score": null,
      "measured_at": "2026-09-25T05:19:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1322.1159437249746,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.08448523875982,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 166,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.9434304636081,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.8496179823456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.565874028835,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.79269831952821,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 130,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 227,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.602479274004,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.69185025593699,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 185,
      "max_score": null,
      "measured_at": "2026-09-23T01:36:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1325.7235521183766,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.45222425187841,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.622039417435602,
      "unilateral_faults": null,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:openai-gpt-oss-120b:07d17099885c6bdb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 170,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.1689877013564,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.706610269607616,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 514,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 182,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 301,
      "max_score": null,
      "measured_at": "2026-09-25T15:14:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 514,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.3619056884113,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.37480073077782,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 213
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 420,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 144,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 279,
      "max_score": null,
      "measured_at": "2026-09-25T02:35:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 420,
      "rating_method": "sequential_elo",
      "raw_elo": 1284.8616505679433,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.966502103404125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 416,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 130,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 270,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 416,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.6530130186823,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.41009124407256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 146
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 492,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 179,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 306,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1280.7711885492126,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.29308716542273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 186
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-terra:4506b3e0a8fb5629",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 133,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 222,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.1709531370514,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.141063215171016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 422,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 133,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 265,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 422,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.8962343284793,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.03360459011067,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 157
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:e037862ab5c7ecb3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 163,
      "max_score": null,
      "measured_at": "2026-09-25T12:53:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1265.6389751628028,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.350179723882725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 161,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.3955730790376,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.740095434691877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meta-muse-glimmer-30b:a614a905445f79d1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 175,
      "max_score": null,
      "measured_at": "2026-09-25T15:41:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1252.2663514681587,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.447809314101196,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 346,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 230,
      "max_score": null,
      "measured_at": "2026-09-25T15:41:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 346,
      "rating_method": "sequential_elo",
      "raw_elo": 1248.0929858646862,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.369602140205416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-5-flash:e1e7937be001cd2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 156,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1250.1823153817916,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Minimal (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.30813306402709,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 412,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 287,
      "max_score": null,
      "measured_at": "2026-09-25T07:49:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 412,
      "rating_method": "sequential_elo",
      "raw_elo": 1243.0906169640273,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.15433037896266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 167,
      "max_score": null,
      "measured_at": "2026-09-25T04:07:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.08501176749,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.827400148127907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemma-4-31b-it:8d94257f5348b920",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 166,
      "max_score": null,
      "measured_at": "2026-09-25T15:41:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1228.862062366313,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.86045609250197,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1228.6763658418904,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.76601471988647,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 164,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1221.9849749023533,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.39953999096173,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 164,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1207.8219281213146,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.40392435260142,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:130c334db8df04f4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1221.2912021064592,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.29044391522753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 168,
      "max_score": null,
      "measured_at": "2026-09-25T13:13:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1188.52176640002,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.11038906658177,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 404,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 298,
      "max_score": null,
      "measured_at": "2026-09-25T06:31:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 404,
      "rating_method": "sequential_elo",
      "raw_elo": 1179.55633657311,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.883171168825367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-27b:47ad2584aeb815bb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 125,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 237,
      "max_score": null,
      "measured_at": "2026-09-24T22:58:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1181.0188896765776,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.78823504946214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 241,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 159,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 241,
      "rating_method": "sequential_elo",
      "raw_elo": 1175.991779846738,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.25307257035454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:openai-gpt-oss-120b:59563b7e90e4a253",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 193,
      "max_score": null,
      "measured_at": "2026-09-25T04:40:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1168.020631803829,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.78906384912377,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 406,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 150,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 270,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 406,
      "rating_method": "sequential_elo",
      "raw_elo": 1169.8764507844362,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.689537637050726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:45ec16f47504b5f5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 188,
      "max_score": null,
      "measured_at": "2026-09-25T06:00:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1158.6186237992895,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.165172475622438,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 175,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1158.245845750152,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.10820746727849,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 274,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 183,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1153.9213565009122,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.88057228629806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 470,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 161,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 350,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 466,
      "rating_method": "sequential_elo",
      "raw_elo": 1116.574474382739,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.234030707551817,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 4,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 280,
      "max_score": null,
      "measured_at": "2026-09-25T02:22:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1102.7019365005071,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.616837033914027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 188,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1101.7822101593483,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.33044730875999,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 272,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 213,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1099.4800470371417,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.225896354434745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-flash:04d7da5a4f2e2af2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 204,
      "max_score": null,
      "measured_at": "2026-09-25T06:12:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1081.8628498304731,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.001881317402578,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 184,
      "max_score": null,
      "measured_at": "2026-09-25T12:53:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1081.7729757022553,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.90537268011971,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-flash:e1a2822fb5bba20e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 241,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1044.8864063083101,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.55490280256513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:mistralai-mistral-medium-3-5:8de2e9417bacc9d3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 248,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1035.7067945105448,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.002668622208688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:inception-mercury-2-5-preview:ff9c957a999941a2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 248,
      "max_score": null,
      "measured_at": "2026-09-25T05:32:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1021.1793636804248,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.029011268175418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 186,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1006.15809921059,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.829926370851808,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 205,
      "max_score": null,
      "measured_at": "2026-09-25T06:31:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 994.9203420266373,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.187537598700027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 202,
      "max_score": null,
      "measured_at": "2026-09-25T04:13:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 988.9738841198142,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.715188962171446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 398,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 341,
      "max_score": null,
      "measured_at": "2026-09-25T05:08:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 398,
      "rating_method": "sequential_elo",
      "raw_elo": 979.2771944650718,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.450085377829959,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:inception-mercury-2-5-preview:f07bc2e66f8341c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 235,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 958.6159767874869,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.772886758516659,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-2:20c65e2b7513d4b4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 236,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 913.1207086604495,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.705163219117038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 210,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 893.9437869150827,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.3532038338859245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 192,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 874.362902625652,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 4.923730589416949,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 212,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 864.0842697939028,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 4.322931554682457,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 272,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:ibm-granite-granite-4-2-8b:49a29e6f1bedcd1d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 260,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Granite 4.2 8B",
      "model_slug": "ibm-granite-granite-4-2-8b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 808.4054617383549,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.7174978039660215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 188,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 802.9446684034115,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.08310002118024254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 224,
      "max_score": null,
      "measured_at": "2026-09-25T00:20:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 799.04601452757,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 20
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-fable-5-1:d307977c9774b8cb",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-intensive",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 2316.7113153732325,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 254
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 418,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 418,
      "rating_method": "sequential_elo",
      "raw_elo": 2154.9857455992246,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 88.12366220504157,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 394
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-6-astra:9acce95ba71bd7c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 2155.9796349618264,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 87.81008055499466,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 241
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 286,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-fable-5:1f4ca1763387a608",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 2103.0202723204475,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 83.86890130218805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 264
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:b4ca94f8b60a9e88",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T05:18:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 2077.0836541057433,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.83360524090116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 239
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:tencent-hy4-preview:014a9ceb67d5b786",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T04:18:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 2070.1983831672133,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.28231996103942,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 230
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-fable-5-1:2ceef8038de90922",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-23T01:57:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 2067.7734288744737,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.17998969178421,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 251
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-6-astra:af89b97f9d676a8c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 2052.9844485033664,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 80.00375714481252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 230
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 408,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 408,
      "rating_method": "sequential_elo",
      "raw_elo": 2044.5328342692478,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 79.71896425856343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 358
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:7f6340c5cd60d7e7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T04:49:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 2038.093778360589,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.84906750984048,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-5-5:12d35a0c8ebcfc9f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T05:11:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 2033.2245619528665,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.55423891820166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-5-5:7dce3bfc0734dff8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T12:23:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 2034.8111199288733,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.51819167485543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.051644180248918,
      "unilateral_faults": 0,
      "wins": 200
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 514,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 180,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T06:20:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 514,
      "rating_method": "sequential_elo",
      "raw_elo": 2013.6159955111561,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.98185391090948,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 455
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-3:650c1432bdd4728a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T06:11:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 2009.920716462801,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.7126928285054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 218
    },
    {
      "admitted_plugins": 0,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-fable-5-1:fdf38228456af115",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "historical-provider-setting-baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 2008.9984085163755,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.66390549772187,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 234
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:2447db730c8d12fe",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T04:00:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1993.1563562965605,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.43253351935807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 214
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c37d073d6b142a09",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T13:41:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1952.230032189293,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.3322501482903,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 219
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-7:f32f0106ab05aad6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T15:53:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1964.1506967203081,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.09523944963898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1941.3225089503185,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.51828642327122,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 233
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-fable-5:346aadd5d76b812b",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-09-25T14:08:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1931.433559611224,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.75317794233399,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 208
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-6:bca3abc3bf41095f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1927.6798227439356,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.46091278477508,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 205
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T06:53:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1928.5600377863639,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.45037043094591,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 183
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 468,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 169,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-09-25T15:24:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 468,
      "rating_method": "sequential_elo",
      "raw_elo": 1921.245931887621,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.8783085249793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 380
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 374,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T14:18:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 374,
      "rating_method": "sequential_elo",
      "raw_elo": 1885.03147903014,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.54145227969542,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 276
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-6-sol:410ceff1171c2cf1",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T04:58:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1896.5477113421146,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.07517430996639,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-6-astra:8883275fa81b106a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T14:04:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1881.6480911845326,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.96573216582014,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 193
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 422,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 422,
      "rating_method": "sequential_elo",
      "raw_elo": 1874.6575974676157,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.84543135872292,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 323
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T05:43:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1869.4824195444983,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.98085473100755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 189
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1864.763508359985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.59804006842714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-7:08dd7ecb5fefd0b4",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-09-25T04:58:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1875.9257072480004,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.39633278537028,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 284,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-spark-1-3:111be2eb4c7d6522",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1856.555157626162,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.14857251600664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 200
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 340,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 340,
      "rating_method": "sequential_elo",
      "raw_elo": 1847.9538628823607,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 64.64982345476963,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 259
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-6-sol:a64b94562f86a4f3",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1856.7161709916622,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 64.02371102656826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 414,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 148,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 414,
      "rating_method": "sequential_elo",
      "raw_elo": 1832.3904048949994,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.62192583535994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 327
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 354,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-09-25T07:48:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 354,
      "rating_method": "sequential_elo",
      "raw_elo": 1832.936624227382,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.542324924259354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 274
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-spark-1-3:4bb11a89323f5400",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T05:50:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1834.236180208509,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.37299941780524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 201
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-6-sol:a790476a054b6a1d",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1813.07111891493,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.76313979266979,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:f9ec308f9bb8850b",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.7833446010702,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.087876316969584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 205
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.5393730240885,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.97193472120926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-8-flash:83795e08736dcbd6",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1771.2634784422758,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.62650606194331,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 176
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1754.109003622718,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.64460987325958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 217
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:091b7e3f3afd6616",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1765.1638806175774,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.09922504114827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 836,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 126,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 351,
      "draws": 126,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 255,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 836,
      "rating_method": "sequential_elo",
      "raw_elo": 1749.339929690285,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.986504745106686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 455
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 688,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 235,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 160,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 688,
      "rating_method": "sequential_elo",
      "raw_elo": 1724.7477595332903,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.276783376822266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 475
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-7:7805d7703d63f406",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T12:33:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1715.9358880058066,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.21796242891374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-6-luna:06fb6314cedafbae",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T12:23:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1710.4022553306731,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.85765337163106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1686.6240042460931,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.520486710806374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 226
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-3:2dbca3140c06e14c",
      "capped_draws": 85,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 85,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-09-24T22:25:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1687.3866173471636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.42314371415959,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 158
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 130,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 127,
      "max_score": null,
      "measured_at": "2026-09-25T15:53:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.5781289256847,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.92441638102823,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 197
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1668.7501849907474,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.86933465904327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 69,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T05:25:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1666.72185236652,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.64642374588417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 448,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 158,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 142,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 448,
      "rating_method": "sequential_elo",
      "raw_elo": 1662.1646153681143,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.16257817471798,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 223
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash:188028ef432c73f8",
      "capped_draws": 101,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 85,
      "max_score": null,
      "measured_at": "2026-09-25T12:33:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.4769087588008,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.423524530455495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.4143031272313,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.23686024714184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 360,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 68,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 113,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 360,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.402338037299,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.19029962085715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 382,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 179,
      "max_score": null,
      "measured_at": "2026-09-25T14:38:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 382,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.4853319623594,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.256103303349285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 194
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-5-5:e7d2796533ceda7c",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 112,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 85,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.3607902781105,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.166191917522255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.335874651846873,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 466,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 140,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 163,
      "draws": 140,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 466,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.5716413839525,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.00613264491125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 192
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 113,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.443424206279,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.47095379427678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 488,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 195,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 167,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 488,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.4996393916958,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.53835062072972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:c69120230888411c",
      "capped_draws": 153,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 133,
      "draws": 153,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T13:20:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.2520417101243,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.29002178163735,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:b85a8fb56d024434",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T15:24:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.5999654523055,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.80742778722643,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 490,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 128,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 167,
      "draws": 128,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 167,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 490,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.9577130546695,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.44050248293845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 912,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 287,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 385,
      "draws": 287,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 303,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 912,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.4008661019027,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.13346770988864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 322
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 356,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 156,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 156,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-09-25T07:15:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 356,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.7341140338356,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.61357997419428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 406,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 156,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 156,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 126,
      "max_score": null,
      "measured_at": "2026-09-25T06:57:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 406,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.6770910024586,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.87599461687681,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 124
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:14b865d3f352c468",
      "capped_draws": 113,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 113,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.2778384363558,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.65121055665382,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max-0902:3772000f789711bc",
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T15:33:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.9079956486037,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.27023916972515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 121,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 121,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.0648943012557,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.23438852520712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 818,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 321,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 265,
      "draws": 321,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 237,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 818,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.2980039687752,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.63782150579934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 260
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-8-flash:e50b23a03b02a00c",
      "capped_draws": 142,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 128,
      "draws": 142,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.3669038906078,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.876211642013004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 1258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 577,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 404,
      "draws": 577,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 368,
      "max_score": null,
      "measured_at": "2026-09-25T13:01:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 1258,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.5589447123277,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.77303881930137,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 313
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-fable-5:9411c67711dccbe8",
      "capped_draws": 118,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T13:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.357739447561,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.23351331310822,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-terra:4506b3e0a8fb5629",
      "capped_draws": 189,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 139,
      "draws": 189,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-09-25T13:20:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 328,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.564014090361,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.99078251203825,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 143,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 143,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T03:04:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.5850329261164,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.47589807230118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d3192451477fbf98",
      "capped_draws": 119,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 119,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.7025958077024,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.3128238460019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 80,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 91,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.0276962334312,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.2889646152446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 451,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 261,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 261,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 120,
      "max_score": null,
      "measured_at": "2026-09-23T04:52:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 451,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.3679003269972,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.85503829239455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 338,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-27b:739c4d774075dc83",
      "capped_draws": 118,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-09-25T02:59:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 338,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.3495104160008,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.556710798345804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 294,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-6:d94ddefd8b9f53eb",
      "capped_draws": 124,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 128,
      "draws": 124,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 294,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.473702042447,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.37146553254912,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 310,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-terra:ac05ef4b9a51340d",
      "capped_draws": 91,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 133,
      "draws": 91,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 310,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.4743152577723,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.506442352056098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 440,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 254,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 152,
      "draws": 254,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-09-25T07:31:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 440,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.0905055647788,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.766163938918144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 354,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-flash:98dfb2fac355b676",
      "capped_draws": 224,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 143,
      "draws": 224,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 92,
      "max_score": null,
      "measured_at": "2026-09-22T12:36:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 354,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.8902635327127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.43340772224031,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 207,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 144,
      "draws": 207,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.4072104012434,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.275745114985668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 286,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 146,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 146,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-09-25T06:53:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.6689339264644,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.704269905633453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-6:aedb1b245d3cd53f",
      "capped_draws": 213,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 161,
      "draws": 213,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 107,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.7735880738578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.691823305388205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5:707323710fb901e4",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 127,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T14:04:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.5429142518308,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.342414005937076,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max-0902:5961da4fe746e1db",
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.4357551604487,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.912822145068468,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 498,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 254,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 156,
      "draws": 254,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 195,
      "max_score": null,
      "measured_at": "2026-09-25T13:41:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 498,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.7530278417635,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.321503645411784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 332,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-terra:bd3aacb7be18fc49",
      "capped_draws": 113,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 113,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 143,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 332,
      "rating_method": "sequential_elo",
      "raw_elo": 1366.4041855520484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.06620879280346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 205,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-09-25T06:05:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.0274390867012,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.84561016247001,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 197,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 197,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T14:08:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.5866683300496,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.69802767311302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 170,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 170,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.142480613769,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.334237110128832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:184634950256ca6a",
      "capped_draws": 203,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-09-25T12:47:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.9512001218188,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.25636287453902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 835,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 299,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 261,
      "draws": 299,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 382,
      "max_score": null,
      "measured_at": "2026-09-25T14:38:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 835,
      "rating_method": "sequential_elo",
      "raw_elo": 1352.5170691998403,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.191386023914582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max-0902:1a5946a1ae31cc68",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.2444001226727,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.045603337595335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro:42034002bcfc5f74",
      "capped_draws": 202,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 202,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T12:23:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.119642213177,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.795680762739188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 218,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 218,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-22T11:44:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.0281060038924,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.744757653812606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 548,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 376,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 164,
      "draws": 376,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 144,
      "max_score": null,
      "measured_at": "2026-09-25T01:53:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 548,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.9574897840018,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.65403469685162,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-3-flash:6bc93e3f26e0f0e5",
      "capped_draws": 197,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 197,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.6593543617612,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.579490120899948,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:78fb6a9e00356b09",
      "capped_draws": 200,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 200,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.9944426793504,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.545702661167372,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 95,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 107,
      "max_score": null,
      "measured_at": "2026-09-25T13:41:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.6382865503635,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.529809756196794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:mistralai-mistral-medium-3-5:e327e1c801399a5f",
      "capped_draws": 192,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 192,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T05:41:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.2196973298408,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.16614110712482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 426,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 279,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 279,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 126,
      "max_score": null,
      "measured_at": "2026-09-25T07:23:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 426,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.3692796598912,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.904305056012785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 920,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 569,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 305,
      "draws": 569,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 292,
      "max_score": null,
      "measured_at": "2026-09-25T14:03:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 920,
      "rating_method": "sequential_elo",
      "raw_elo": 1332.1302501376986,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.70917520967793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 29,
      "draws": 180,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.476054487212,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.699884578572615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.672227745205968,
      "unilateral_faults": null,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-27b:3dc939e9daa83d91",
      "capped_draws": 221,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 221,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-09-25T05:43:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 328,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.439317034092,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.6290352177258,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 280,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:openai-gpt-oss-120b:59563b7e90e4a253",
      "capped_draws": 187,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 187,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T07:31:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 280,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.223467236304,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.55119688247162,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:inception-mercury-2-5-preview:f07bc2e66f8341c5",
      "capped_draws": 212,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 212,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.5935405101955,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.490331698828758,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 296,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-spark-1-3:22ddc49b675eb171",
      "capped_draws": 202,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 202,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1333.7086722472022,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.485658092588114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 454,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 334,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 163,
      "draws": 334,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T05:43:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 454,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.7795078566724,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.469391155270593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 882,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 616,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 280,
      "draws": 616,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 229,
      "max_score": null,
      "measured_at": "2026-09-25T13:41:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 882,
      "rating_method": "sequential_elo",
      "raw_elo": 1325.1732080243237,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.154938909796876,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:45ec16f47504b5f5",
      "capped_draws": 205,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.8407636259985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.074351406838364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 179,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 179,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-25T05:23:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.808197108261,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.98137516072915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 479,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 266,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 150,
      "draws": 266,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 177,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 479,
      "rating_method": "sequential_elo",
      "raw_elo": 1321.1467474377516,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.907908985401132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:tencent-hy4-preview:2077a0aa15ce66b2",
      "capped_draws": 214,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 214,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 115,
      "max_score": null,
      "measured_at": "2026-09-25T14:13:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1321.0852609664673,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.654353233120247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:e0a2978fff9e81b1",
      "capped_draws": 181,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 181,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1322.8531658008642,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.618335850851498,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 363,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 229,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 151,
      "draws": 229,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-09-25T13:01:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 363,
      "rating_method": "sequential_elo",
      "raw_elo": 1319.773428227486,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.597994074361377,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 304,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-flash:e1a2822fb5bba20e",
      "capped_draws": 203,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 304,
      "rating_method": "sequential_elo",
      "raw_elo": 1321.2787153819802,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.565120302446235,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-3-flashx:43f4326da261c154",
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.4329200529928,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.546741166561926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 403,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 252,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 133,
      "draws": 252,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 136,
      "max_score": null,
      "measured_at": "2026-09-25T06:15:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 403,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.5766304670988,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.51205331176168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 204,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 204,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-22T22:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1321.1854784744369,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.49170866946286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 169,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 169,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T15:10:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1322.3451540972053,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.444795053368917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 338,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-8-flash:6b8b02f1f727feff",
      "capped_draws": 190,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 190,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 128,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 338,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.3303361458036,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.43076525829919,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-glimmer-30b:085624a1bd2a3883",
      "capped_draws": 191,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 191,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T15:08:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.9198277734108,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.41122888408428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 145,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 145,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.722949607299,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.396279962390953,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 532,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 420,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 222,
      "draws": 420,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-09-25T05:56:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 532,
      "rating_method": "sequential_elo",
      "raw_elo": 1319.8843881862263,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.339256932464274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 190,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 190,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T13:41:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1319.5573778937342,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.3217018950558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 532,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 393,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 192,
      "draws": 393,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 113,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 532,
      "rating_method": "sequential_elo",
      "raw_elo": 1319.3611201675367,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.298898663270595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 171,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 171,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.1696200624187,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.23875235015678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 834,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 586,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 255,
      "draws": 586,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 211,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 834,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.516631196398,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.228912691343204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 199,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 199,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.7216823557662,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.208092923512243,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 168,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 168,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T13:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1319.3025413145217,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.181292624255057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 158,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 158,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.166016388608,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.17361563218513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 225,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 225,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T13:41:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.0055779922611,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.161433575276742,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 876,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 600,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 267,
      "draws": 600,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 243,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 876,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.1806123108736,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.086761769650685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 608,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 437,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 194,
      "draws": 437,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 141,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 606,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.988025781403,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.0086745606863,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-glimmer-30b:20d2aea9e268d0ef",
      "capped_draws": 197,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 197,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.1836103666499,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.82381936834102,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:bytedance-seed-seed-2-0-code:e037862ab5c7ecb3",
      "capped_draws": 191,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 191,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-09-25T06:15:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.029726376838,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.681044835220536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 542,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 382,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 187,
      "draws": 382,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 141,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 542,
      "rating_method": "sequential_elo",
      "raw_elo": 1309.5085507135805,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.568927521142058,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash:e1e7937be001cd2a",
      "capped_draws": 182,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 182,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1309.6621091886293,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Minimal (historical request variant 2)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.542190014754578,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-glimmer-30b:a614a905445f79d1",
      "capped_draws": 193,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 193,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T07:01:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1309.115476003638,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.50068426102481,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 159,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 159,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1307.6036854276551,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.341126712427066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 288,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:tencent-hy4-preview:b8e7119f660161ad",
      "capped_draws": 193,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 193,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1305.355782588245,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.308602589729603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro:c11fecb63644464d",
      "capped_draws": 184,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 184,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T03:22:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1306.1903913845374,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.278583142445555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 202,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 202,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1305.0370526777124,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.265561771241,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 176,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 176,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T15:10:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1305.335449504434,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.234910904260282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 237,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 237,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.9500960874611,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.215459853296952,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 408,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 268,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 268,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T14:04:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 408,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.8401973546747,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.17459402857645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 476,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 306,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 177,
      "draws": 306,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 148,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 476,
      "rating_method": "sequential_elo",
      "raw_elo": 1304.842053061372,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.090756402914224,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 329,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 203,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 130,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 115,
      "max_score": null,
      "measured_at": "2026-09-25T07:01:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 329,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.7855986250888,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.076253765208513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 154,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 154,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1304.7523394763623,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Medium (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.05104114701348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash:a0af36e4d0bc99b5",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 127,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1307.31094474855,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Low (historical request variant 1)",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.96074784327254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "draws": 184,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-09-25T05:43:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.9228461053442,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.811014682700467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.465140987172258,
      "unilateral_faults": null,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 274,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:ibm-granite-granite-4-2-8b:49a29e6f1bedcd1d",
      "capped_draws": 199,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 199,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Granite 4.2 8B",
      "model_slug": "ibm-granite-granite-4-2-8b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1297.7581063353189,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.686800313770597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 146,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 146,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-23T15:51:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.6831239572457,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.6593423326237,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 330,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:mistralai-mistral-medium-3-5:8de2e9417bacc9d3",
      "capped_draws": 198,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 198,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 116,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 330,
      "rating_method": "sequential_elo",
      "raw_elo": 1294.977609210738,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.63778170243964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:130c334db8df04f4",
      "capped_draws": 68,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1309.6429151589853,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.484542801549498,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 160,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 160,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 85,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1294.3553301644727,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.372704564395118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-6-luna:dfbe27d870893a52",
      "capped_draws": 57,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1306.792176313163,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.372054943804372,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 257,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 257,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-09-25T14:13:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1288.4683412899717,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.172996399426747,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 167,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 167,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-09-25T15:08:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1288.8790098390712,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.86286226948965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 162,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 162,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1283.4622351785426,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.587850473736427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 408,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 284,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 284,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-09-25T05:30:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 408,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.7831903055633,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.499809680072865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T06:15:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1278.7602474587914,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.27036895059496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 286,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:20c65e2b7513d4b4",
      "capped_draws": 209,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 209,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.207605245957,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.16510261667805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 157,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 157,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.5376688345202,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.012483894295887,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-3-flash:1540ade2fda6b881",
      "capped_draws": 201,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 201,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.5083937551233,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.64380726893646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:3fe477f1e3ed7e39",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1280.841049518355,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.29762262352045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-3-flashx:746a19cef7ee23ef",
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1279.1318672273992,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.111374859763473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:openai-gpt-oss-120b:07d17099885c6bdb",
      "capped_draws": 194,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 194,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1262.3682714492068,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.96542035285595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 412,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 257,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 257,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 151,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 412,
      "rating_method": "sequential_elo",
      "raw_elo": 1254.6639903797159,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.75166353849725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:inception-mercury-2-5-preview:ff9c957a999941a2",
      "capped_draws": 182,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 118,
      "draws": 182,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1256.9096105084075,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.591805674533738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 284,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:openai-gpt-oss-120b:7e4ecfa424847773",
      "capped_draws": 192,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 192,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1252.1798924471577,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.258473624041308,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 155,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 155,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T14:08:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1253.5592248137123,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.252817076331517,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-6-luna:3dfecd4fa4d78509",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.9720176074093,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.12822117287516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d0b5b92265541548",
      "capped_draws": 185,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 185,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-09-25T07:31:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1239.8410226636497,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.340229382396092,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:4571486d5f3c5826",
      "capped_draws": 162,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 162,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 98,
      "max_score": null,
      "measured_at": "2026-09-25T05:56:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1240.0094213952332,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "High (historical request variant 1)",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.253474683256968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 138,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 138,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T15:33:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1214.770657236529,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.26871518944819,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:9b3aa3914934b08c",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1224.9878973868924,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.135717854305447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-3:9e30a36ab00bd740",
      "capped_draws": 155,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 155,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1202.2009674708343,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.38984780565305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:04d7da5a4f2e2af2",
      "capped_draws": 133,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 133,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1201.3201181817356,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.337046587683027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash:79befaaad7974375",
      "capped_draws": 135,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 135,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 126,
      "max_score": null,
      "measured_at": "2026-09-22T10:58:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1201.1802064230644,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.312341613513716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:d1c3d52890a12a42",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1210.6336257419828,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.910316416776945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 108,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 108,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-09-25T04:28:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1195.049897991347,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Medium (historical request variant 1)",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.763253915121723,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 286,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-3-flash:22cd36959459fbdd",
      "capped_draws": 144,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 144,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 136,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1149.9019136121656,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.498805673082217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 348,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 267,
      "max_score": null,
      "measured_at": "2026-09-25T07:15:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 348,
      "rating_method": "sequential_elo",
      "raw_elo": 1110.857285273001,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.701180641503443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-3-flashx:d5d0648c410f1ae2",
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1109.1345222853001,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.080049745365206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 198,
      "max_score": null,
      "measured_at": "2026-09-25T05:25:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1000.1996922567068,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-6-astra:ae2dbe5eab26d175",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 24
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 1.47583,
        "mean": 0.6505529166666667,
        "median": 0.40659249999999997,
        "min": 0.2072175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-05": 24
        },
        "run_count": 24,
        "token_priced_attempt_count": 24,
        "total": 15.613270000000004
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 552,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 24,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:34:00Z",
      "losses": 454,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 50.02617127882385,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5840,
      "rating_method": "sequential_elo",
      "raw_elo": 2030.7455773038223,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 84.30845411421939,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 4834
    },
    {
      "admitted_plugins": 27,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-fable-5-1:4036efb3e80cec89",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 27,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 30
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 11.79121,
        "mean": 2.3225539838420417,
        "median": 1.126127596791556,
        "min": 0.6566066208996896,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 20,
          "boardgame-list-prices-2026-09-08": 10
        },
        "run_count": 27,
        "token_priced_attempt_count": 30,
        "total": 64.31171957781585
      },
      "codegen_evaluated_cells": 27,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 448,
      "eligibility_flag": true,
      "entry_count": 27,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 24,
      "first_pass_rate": 0.8888888888888888,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "infra_failures_excluded": 5,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:05:54Z",
      "losses": 604,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 27.6720155573788,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6458,
      "rating_method": "sequential_elo",
      "raw_elo": 1999.0743591304715,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 80.32247446404502,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 5406
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-opus-5-5:90223050ff456e01",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 26,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 30
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 3.092384,
        "mean": 0.8124949166666666,
        "median": 0.267474,
        "min": 0.094852,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 30
        },
        "run_count": 27,
        "token_priced_attempt_count": 30,
        "total": 21.736292
      },
      "codegen_evaluated_cells": 26,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 176,
      "eligibility_flag": true,
      "entry_count": 26,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 23,
      "first_pass_rate": 0.8846153846153846,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:34:00Z",
      "losses": 252,
      "max_score": 90.00227559221021,
      "measured_at": null,
      "min_score": 34.34311959065729,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2354,
      "rating_method": "sequential_elo",
      "raw_elo": 1897.3138612223452,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.11538461538461539,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 71.7363298403025,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1926
    },
    {
      "admitted_plugins": 41,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-opus-5:2db917d562130aa3",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 41,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 48
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 7,
        "max": 2.09943,
        "mean": 0.703821875,
        "median": 0.48028875,
        "min": 0.2178175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 48
        },
        "run_count": 48,
        "token_priced_attempt_count": 48,
        "total": 33.78345000000001
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1172,
      "eligibility_flag": true,
      "entry_count": 41,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 41,
      "first_pass_rate": 0.8541666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:14:25Z",
      "losses": 1355,
      "max_score": 90.34746663281791,
      "measured_at": null,
      "min_score": 15.978871709726342,
      "model_code_failure_rate": 0.14583333333333334,
      "model_code_failures": 7,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 8401,
      "rating_method": "sequential_elo",
      "raw_elo": 1836.5273334882852,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 63.4848578652761,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 5874
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:z-ai-glm-5-3:56eeba387b2e14bb",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 26
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.5256212,
        "mean": 0.19965798354166664,
        "median": 0.1553977,
        "min": 0.0217974,
        "recorded_attempt_count": 26,
        "run_count": 24,
        "total": 4.791791605
      },
      "codegen_evaluated_cells": 23,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1311,
      "eligibility_flag": false,
      "entry_count": 23,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.9130434782608695,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-04"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:12Z",
      "losses": 1419,
      "max_score": 97.58127501121015,
      "measured_at": null,
      "min_score": 15.003603712634062,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 6051,
      "rating_method": "sequential_elo",
      "raw_elo": 1768.9116795478662,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 2,
      "repaired_rate": 0.08695652173913043,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 59.630468776642225,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 3321
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-6-sol:0a1f83515d3cebb3",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 1.17244375,
        "mean": 0.3844993229166666,
        "median": 0.23243875,
        "min": 0.10071375,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 25
        },
        "run_count": 24,
        "token_priced_attempt_count": 25,
        "total": 9.227983749999998
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1327,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 23,
      "first_pass_rate": 0.9583333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:44Z",
      "losses": 2172,
      "max_score": 89.24673663502878,
      "measured_at": null,
      "min_score": 9.182072363962202,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 8348,
      "rating_method": "sequential_elo",
      "raw_elo": 1701.6229680149643,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 56.25083621933663,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 4849
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:x-ai-grok-4-7:fb7fa57036d697f2",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 20,
        "cost_basis_counts": {
          "provider_reported": 22
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.5756864,
        "mean": 0.20675944000000004,
        "median": 0.1363672,
        "min": 0.0,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 19
        },
        "recorded_attempt_count": 22,
        "run_count": 20,
        "total": 4.135188800000001
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 149,
      "eligibility_flag": false,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 15,
      "first_pass_rate": 0.8823529411764706,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:22:25Z",
      "losses": 388,
      "max_score": 81.37689077370601,
      "measured_at": null,
      "min_score": 15.846953534414173,
      "model_code_failure_rate": 0.058823529411764705,
      "model_code_failures": 1,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1404,
      "rating_method": "sequential_elo",
      "raw_elo": 1706.2464980654577,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.058823529411764705,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 55.56389904720976,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 867
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-6-sol:98006d193d583881",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.225321,
        "mean": 0.10943510416666667,
        "median": 0.0772785,
        "min": 0.033231000000000004,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 25
        },
        "run_count": 24,
        "token_priced_attempt_count": 25,
        "total": 2.626442500000001
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 321,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 23,
      "first_pass_rate": 0.9583333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:29:47Z",
      "losses": 479,
      "max_score": 82.55615873333252,
      "measured_at": null,
      "min_score": 11.206070516617746,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2132,
      "rating_method": "sequential_elo",
      "raw_elo": 1722.755665585547,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 55.130665986153616,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1332
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-fable-5:13ae1db461acc087",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 24
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 2.14955,
        "mean": 0.7608541666666667,
        "median": 0.47084000000000004,
        "min": 0.22654,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 24
        },
        "run_count": 24,
        "token_priced_attempt_count": 24,
        "total": 18.260500000000004
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 1219,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 24,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:59:44Z",
      "losses": 1627,
      "max_score": 85.53702993381843,
      "measured_at": null,
      "min_score": 8.30135369548809,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6037,
      "rating_method": "sequential_elo",
      "raw_elo": 1706.7445880982295,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 54.9946056456668,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 3191
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:x-ai-grok-4-6:de845d6d61a8ca84",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 27
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.28029,
        "mean": 0.13107158333333335,
        "median": 0.12371399999999999,
        "min": 0.027072,
        "recorded_attempt_count": 27,
        "run_count": 24,
        "total": 3.1457180000000005
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1842,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:19:40Z",
      "losses": 1934,
      "max_score": 80.29583807622168,
      "measured_at": null,
      "min_score": 12.14033355812917,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6495,
      "rating_method": "sequential_elo",
      "raw_elo": 1610.6480157981046,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 47.70725999383137,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2719
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-4:c444884bfba7584b",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 27
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 2.2530275,
        "mean": 0.6328307291666667,
        "median": 0.26543625,
        "min": 0.0656625,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 27
        },
        "run_count": 24,
        "token_priced_attempt_count": 27,
        "total": 15.187937499999997
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2190,
      "eligibility_flag": true,
      "entry_count": 23,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:05:53Z",
      "losses": 2280,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.041666666666666664,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 7957,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.359247792996,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 2,
      "repaired_rate": 0.08333333333333333,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 46.96953695880148,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 3487
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:z-ai-glm-5-3-flash:b7f0d7586457fa6c",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.02871725,
        "mean": 0.008139411458333334,
        "median": 0.005035225,
        "min": 0.001111625,
        "recorded_attempt_count": 28,
        "run_count": 24,
        "total": 0.19534587500000003
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 1665,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 20,
      "first_pass_rate": 0.8333333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:25:14Z",
      "losses": 2100,
      "max_score": 73.9709651519967,
      "measured_at": null,
      "min_score": 11.498805673082217,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6321,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.7925249803666,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 4,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 46.898262367885415,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2556
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:xiaomi-mimo-v2-6-pro:d87db7f47c3dd584",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 13,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.1085880432,
        "mean": 0.03556378255384615,
        "median": 0.010081125,
        "min": 0.005105595,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 15
        },
        "recorded_attempt_count": 15,
        "run_count": 13,
        "total": 0.4623291732
      },
      "codegen_evaluated_cells": 13,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 276,
      "eligibility_flag": false,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 11,
      "first_pass_rate": 0.8461538461538461,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality",
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:57:09Z",
      "losses": 381,
      "max_score": 77.84906750984048,
      "measured_at": null,
      "min_score": 3.415118568191135,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1190,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 2,
      "repaired_rate": 0.15384615384615385,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 46.79780243156552,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 533
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-8-flash:2a6a0471e29241b9",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 25
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.2764612177973556,
        "mean": 0.08231859375,
        "median": 0.06440174762499168,
        "min": 0.026892580852245062,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 25
        },
        "run_count": 24,
        "token_priced_attempt_count": 25,
        "total": 1.9756462499999996
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1558,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 23,
      "first_pass_rate": 0.9583333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:19:38Z",
      "losses": 2045,
      "max_score": 83.10880420461697,
      "measured_at": null,
      "min_score": 7.419192145713985,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6446,
      "rating_method": "sequential_elo",
      "raw_elo": 1606.102633128222,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 46.67661792110753,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2843
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:x-ai-grok-4-5:8eb1badb0c39eeb6",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.13495079999999998,
        "mean": 0.07082726666666667,
        "median": 0.0661398,
        "min": 0.0424244,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 34
        },
        "recorded_attempt_count": 34,
        "run_count": 24,
        "total": 1.6998543999999998
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1983,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 20,
      "first_pass_rate": 0.8333333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:29Z",
      "losses": 2538,
      "max_score": 79.71896425856343,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 8261,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.8004093094323,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 4,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 45.66075557967151,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 3740
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:meta-muse-spark-1-3:ccaff938efc69b13",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 23,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.273243,
        "mean": 0.0832670543478261,
        "median": 0.04626,
        "min": 0.0,
        "recorded_attempt_count": 24,
        "run_count": 23,
        "total": 1.9151422500000002
      },
      "codegen_evaluated_cells": 22,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1333,
      "eligibility_flag": false,
      "entry_count": 22,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.9545454545454546,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-05"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:55Z",
      "losses": 1896,
      "max_score": 78.27779768942712,
      "measured_at": null,
      "min_score": 13.707425405221867,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 5749,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.6507186686704,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.045454545454545456,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 45.43028210629307,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2520
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:tencent-hy4-preview:099a318abd9bb600",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.190258393,
        "mean": 0.09097980808333334,
        "median": 0.1119999555,
        "min": 0.009391185,
        "recorded_attempt_count": 28,
        "run_count": 24,
        "total": 2.183515394
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1643,
      "eligibility_flag": true,
      "entry_count": 23,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 20,
      "first_pass_rate": 0.8333333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:00Z",
      "losses": 2037,
      "max_score": 81.28231996103942,
      "measured_at": null,
      "min_score": 9.957083818816807,
      "model_code_failure_rate": 0.041666666666666664,
      "model_code_failures": 1,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6247,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.5304721558375,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 45.09619040783053,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2567
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-opus-4-8:890495dbb6c94c7c",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 25
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 1.38945,
        "mean": 0.43567666666666666,
        "median": 0.20305499999999999,
        "min": 0.131495,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 25
        },
        "run_count": 24,
        "token_priced_attempt_count": 25,
        "total": 10.456240000000001
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1281,
      "eligibility_flag": true,
      "entry_count": 22,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:52:48Z",
      "losses": 1329,
      "max_score": 78.12478117978807,
      "measured_at": null,
      "min_score": 9.918422916272286,
      "model_code_failure_rate": 0.08333333333333333,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4774,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.9729849277508,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 43.68486599242672,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2164
    },
    {
      "admitted_plugins": 42,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-6-flash:bc54536515b1fe37",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 42,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 126
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.531673125,
        "mean": 0.264606278125,
        "median": 0.24728879999999998,
        "min": 0.0411735,
        "recorded_attempt_count": 126,
        "run_count": 48,
        "total": 12.701101349999998
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 4260,
      "eligibility_flag": true,
      "entry_count": 42,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 34,
      "first_pass_rate": 0.7083333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:41:54Z",
      "losses": 5278,
      "max_score": 84.32762532825016,
      "measured_at": null,
      "min_score": 7.58639288876681,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 6,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 16123,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.7156187142796,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 42.63117632436954,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 6585
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-4-1-nano:27769ccf83edf63d",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 1,
        "cost_basis_counts": {
          "estimated": 1,
          "local_standard_estimate": 1
        },
        "cost_is_complete": false,
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "max": 0.0023425,
        "mean": 0.0023425,
        "median": 0.0023425,
        "min": 0.0023425,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 1,
          "boardgame-list-prices-2026-09-08": 1
        },
        "recorded_attempt_count": 1,
        "run_count": 1,
        "token_priced_attempt_count": 1,
        "total": 0.0023425
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 55,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": 1,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 1,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality",
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-24T07:37:25Z",
      "losses": 167,
      "max_score": 42.384495360660594,
      "measured_at": null,
      "min_score": 42.384495360660594,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 400,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 42.384495360660594,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 160
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-8-2-4t-a95b:9c636bff3b95eabb",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 27
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.7896974949512139,
        "mean": 0.22795366666666664,
        "median": 0.16679960729572763,
        "min": 0.07156210251142602,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 27
        },
        "run_count": 24,
        "token_priced_attempt_count": 27,
        "total": 5.470887999999999
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1983,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:20:11Z",
      "losses": 2125,
      "max_score": 81.83360524090116,
      "measured_at": null,
      "min_score": 13.524183164803983,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6524,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.9453433860585,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 42.35355583567759,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2416
    },
    {
      "admitted_plugins": 79,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:stealth-ox-alpha:73d3ab9aca3d929b",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 79,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 112
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 112,
        "run_count": 88,
        "total": 0.0
      },
      "codegen_evaluated_cells": 85,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 5385,
      "eligibility_flag": true,
      "entry_count": 79,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 62,
      "first_pass_rate": 0.7294117647058823,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "infra_failures_excluded": 5,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:17:09Z",
      "losses": 7533,
      "max_score": 67.13193639618068,
      "measured_at": null,
      "min_score": 13.796926219903233,
      "model_code_failure_rate": 0.07058823529411765,
      "model_code_failures": 6,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 21317,
      "rating_method": "sequential_elo",
      "raw_elo": 1533.117554059444,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 17,
      "repaired_rate": 0.2,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 42.271968576040024,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 8399
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-5-flash:2fe322b9f9e7e988",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 30,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 32,
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Combined: Provider-reported + Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.5094276945411561,
        "mean": 0.1819473937669366,
        "median": 0.18692147314407714,
        "min": 0.043710665151447045,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 32
        },
        "recorded_attempt_count": 14,
        "run_count": 32,
        "token_priced_attempt_count": 32,
        "total": 4.9824165
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1970,
      "eligibility_flag": false,
      "entry_count": 30,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 16,
      "first_pass_rate": 0.6666666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:25:05Z",
      "losses": 2629,
      "max_score": 85.75732154194154,
      "measured_at": null,
      "min_score": 5.490992930648422,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 7185,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.693226172194,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 41.052071787529606,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2586
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-5:1f9b0e6a5daf3f13",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 26
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 4.4173,
        "mean": 1.10693125,
        "median": 0.4176025,
        "min": 0.12078,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 26
        },
        "run_count": 24,
        "token_priced_attempt_count": 26,
        "total": 26.566350000000003
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1638,
      "eligibility_flag": true,
      "entry_count": 22,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-06"
      ],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:10:59Z",
      "losses": 1185,
      "max_score": 85.64043148326957,
      "measured_at": null,
      "min_score": 10.026592849743277,
      "model_code_failure_rate": 0.08333333333333333,
      "model_code_failures": 2,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4599,
      "rating_method": "sequential_elo",
      "raw_elo": 1568.467758387628,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 40.87754223283814,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1776
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:z-ai-glm-5-3-flashx:4100dadd8ed38338",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.09557687,
        "mean": 0.03177873833333334,
        "median": 0.025158225,
        "min": 0.00543595,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 29
        },
        "recorded_attempt_count": 29,
        "run_count": 24,
        "total": 0.7626897200000001
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 526,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 19,
      "first_pass_rate": 0.7916666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:21:47Z",
      "losses": 752,
      "max_score": 71.74427757233467,
      "measured_at": null,
      "min_score": 7.080049745365206,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2129,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.8038895736838,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333334,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 40.837786212448485,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 851
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:xiaomi-mimo-v2-6-flash:492403cf5d25ef55",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 23
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.02304638,
        "mean": 0.01037612625,
        "median": 0.0072198,
        "min": 0.00188342,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 23
        },
        "recorded_attempt_count": 23,
        "run_count": 16,
        "total": 0.16601801999999996
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 300,
      "eligibility_flag": false,
      "entry_count": 15,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T12:06:40Z",
      "losses": 504,
      "max_score": 73.64786897600108,
      "measured_at": null,
      "min_score": 11.524793275000588,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1324,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 40.78318198083055,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 520
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-8-max-0902:077c2f0da5fabd7f",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.606316,
        "mean": 0.18673533333333334,
        "median": 0.11641699999999999,
        "min": 0.0,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 28
        },
        "recorded_attempt_count": 29,
        "run_count": 24,
        "total": 4.481648
      },
      "codegen_evaluated_cells": 23,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 569,
      "eligibility_flag": false,
      "entry_count": 23,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 18,
      "first_pass_rate": 0.782608695652174,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-07"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:19:18Z",
      "losses": 586,
      "max_score": 76.38881018245638,
      "measured_at": null,
      "min_score": 2.3421974844057343,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1935,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.32752898177,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 5,
      "repaired_rate": 0.21739130434782608,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 40.764197249873504,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 780
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:moonshotai-kimi-k3:588742aa6ac9e321",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 40
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.6279041999999999,
        "mean": 0.2975122,
        "median": 0.2990655,
        "min": 0.0550338,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 40
        },
        "recorded_attempt_count": 40,
        "run_count": 24,
        "total": 7.1402928
      },
      "codegen_evaluated_cells": 23,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2741,
      "eligibility_flag": false,
      "entry_count": 21,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-05",
        "GB2-06"
      ],
      "first_pass_admitted": 15,
      "first_pass_rate": 0.6521739130434783,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:19Z",
      "losses": 2867,
      "max_score": 88.12366220504157,
      "measured_at": null,
      "min_score": 10.856245227633352,
      "model_code_failure_rate": 0.08695652173913043,
      "model_code_failures": 2,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 8856,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.2165370873972,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 6,
      "repaired_rate": 0.2608695652173913,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 40.144514399459716,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 3248
    },
    {
      "admitted_plugins": 17,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:meta-muse-spark-1-2:24ca876a504f091c",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 17,
        "cell_count": 18,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.143734,
        "mean": 0.04530390277777777,
        "median": 0.035486000000000004,
        "min": 0.01939525,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 20
        },
        "recorded_attempt_count": 20,
        "run_count": 18,
        "total": 0.8154702500000001
      },
      "codegen_evaluated_cells": 18,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1413,
      "eligibility_flag": false,
      "entry_count": 17,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 16,
      "first_pass_rate": 0.8888888888888888,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:22:13Z",
      "losses": 2390,
      "max_score": 72.07963331402082,
      "measured_at": null,
      "min_score": 8.986553392204476,
      "model_code_failure_rate": 0.05555555555555555,
      "model_code_failures": 1,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 6216,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.2769150330819,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.05555555555555555,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 39.74610318614332,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2413
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:deepseek-deepseek-v4-1-flash:b9ebacea37464f0c",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 26
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.031583268,
        "mean": 0.0163638035,
        "median": 0.017740284000000002,
        "min": 0.00220635,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 26
        },
        "recorded_attempt_count": 26,
        "run_count": 24,
        "total": 0.392731284
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 592,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 22,
      "first_pass_rate": 0.9166666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:23Z",
      "losses": 638,
      "max_score": 75.19336305189155,
      "measured_at": null,
      "min_score": 11.271801424400126,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2038,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.6107368485566,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 2,
      "repaired_rate": 0.08333333333333333,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 39.5737668556252,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 808
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-8-max:0a2909a34622f950",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 30
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.40721066666666667,
        "mean": 0.19033848611111112,
        "median": 0.13741799999999998,
        "min": 0.066054,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 30
        },
        "recorded_attempt_count": 30,
        "run_count": 29,
        "total": 6.452750000000002
      },
      "codegen_evaluated_cells": 26,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2055,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 24,
      "first_pass_rate": 0.9230769230769231,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-08"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:44Z",
      "losses": 2298,
      "max_score": 90.1443955387162,
      "measured_at": null,
      "min_score": 11.88308300278399,
      "model_code_failure_rate": 0.07692307692307693,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6653,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.4546822618704,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.5215870238904,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2300
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-opus-4-5:e04fe29aa9cb387c",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 39,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 41
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.512955,
        "mean": 0.2537023958333333,
        "median": 0.20905875000000002,
        "min": 0.09594,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 16,
          "boardgame-list-prices-2026-08-08": 25
        },
        "run_count": 40,
        "token_priced_attempt_count": 41,
        "total": 11.203785
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2345,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 24,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:30Z",
      "losses": 3097,
      "max_score": 66.84543135872292,
      "measured_at": null,
      "min_score": 9.818228255319736,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 8542,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.5874639910728,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 37.078567235002424,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 3100
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-sonnet-5:2e363afacad82877",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 24
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.50466,
        "mean": 0.15942958333333332,
        "median": 0.068377,
        "min": 0.049908,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 24
        },
        "run_count": 24,
        "token_priced_attempt_count": 24,
        "total": 3.8263099999999994
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2456,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 24,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:44:45Z",
      "losses": 3310,
      "max_score": 64.64982345476963,
      "measured_at": null,
      "min_score": 9.60693783512406,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 8713,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.8328598578287,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 37.01633038301636,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2947
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-8-flash:0eaf9e05a2b2ee2e",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 22
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.061982706,
        "mean": 0.020562389374999997,
        "median": 0.015992453,
        "min": 0.0021123,
        "recorded_attempt_count": 22,
        "run_count": 16,
        "total": 0.32899822999999995
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1535,
      "eligibility_flag": false,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 10,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:55Z",
      "losses": 1531,
      "max_score": 74.00144873524822,
      "measured_at": null,
      "min_score": 8.785005477286392,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 4391,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 36.95000270048291,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1325
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-8-27b:325c4507f070dddc",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 41
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.3521656,
        "mean": 0.08683453949999999,
        "median": 0.042413385,
        "min": 0.0,
        "recorded_attempt_count": 41,
        "run_count": 24,
        "total": 2.0840289480000003
      },
      "codegen_evaluated_cells": 23,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 850,
      "eligibility_flag": false,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.34782608695652173,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold",
        "fixed_coverage_incomplete",
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:33:49Z",
      "losses": 1469,
      "max_score": 74.90167026913919,
      "measured_at": null,
      "min_score": 20.202011632004123,
      "model_code_failure_rate": 0.391304347826087,
      "model_code_failures": 9,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3889,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 6,
      "repaired_rate": 0.2608695652173913,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.99205923506444,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1570
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:deepseek-deepseek-v4-pro:7bb1ed45eb8d62a0",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.176790095,
        "mean": 0.062023549123500006,
        "median": 0.0458058365,
        "min": 0.014466934,
        "recorded_attempt_count": 35,
        "run_count": 24,
        "total": 1.488565178964
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1747,
      "eligibility_flag": true,
      "entry_count": 22,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-06"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.5416666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:59:44Z",
      "losses": 2136,
      "max_score": 75.28091626993594,
      "measured_at": null,
      "min_score": 9.212833783417654,
      "model_code_failure_rate": 0.08333333333333333,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6000,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.7697397439342,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.89201437659667,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2117
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-6-terra:155aa79eccdb43f8",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 28
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.45800250000000003,
        "mean": 0.18569479166666666,
        "median": 0.091314375,
        "min": 0.058876874999999995,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 28
        },
        "run_count": 24,
        "token_priced_attempt_count": 28,
        "total": 4.456675
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2032,
      "eligibility_flag": true,
      "entry_count": 23,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-05"
      ],
      "first_pass_admitted": 20,
      "first_pass_rate": 0.8333333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:26:41Z",
      "losses": 2328,
      "max_score": 76.93585154551911,
      "measured_at": null,
      "min_score": 12.122561741654145,
      "model_code_failure_rate": 0.041666666666666664,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6460,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.8286890336062,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.78022683442092,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2100
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:deepseek-deepseek-v4-pro-0813:e0f8ea8c59cf3cd4",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 31
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.28337826924,
        "mean": 0.09905735158166666,
        "median": 0.10177922040000001,
        "min": 0.01808105112,
        "recorded_attempt_count": 31,
        "run_count": 24,
        "total": 2.37737643796
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1868,
      "eligibility_flag": true,
      "entry_count": 22,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-05"
      ],
      "first_pass_admitted": 18,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:12Z",
      "losses": 2168,
      "max_score": 71.8729308953561,
      "measured_at": null,
      "min_score": 8.629972723433358,
      "model_code_failure_rate": 0.08333333333333333,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6050,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.48887175413,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 4,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.707533898763096,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2014
    },
    {
      "admitted_plugins": 32,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:z-ai-glm-5-2:50fed1035ee7c556",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 48,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 72
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.39278997800000004,
        "mean": 0.09944282164861112,
        "median": 0.056673037849999996,
        "min": 0.013816857666666668,
        "recorded_attempt_count": 72,
        "run_count": 48,
        "total": 3.5146565168000006
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 3727,
      "eligibility_flag": true,
      "entry_count": 48,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 16,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:05:48Z",
      "losses": 3961,
      "max_score": 73.77006751900642,
      "measured_at": null,
      "min_score": 7.705163219117038,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 10928,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.4282482107042,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 16,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.91133708337777,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 3240
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5:afe5edea083200ed",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 31
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 3,
        "max": 0.45464499999999997,
        "mean": 0.18566328125000006,
        "median": 0.17276625,
        "min": 0.06945125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 12,
          "boardgame-list-prices-2026-08-08": 19
        },
        "run_count": 24,
        "token_priced_attempt_count": 31,
        "total": 4.455918750000001
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1233,
      "eligibility_flag": false,
      "entry_count": 21,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 16,
      "first_pass_rate": 0.6666666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "untested_or_ineligible_settings",
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T12:56:44Z",
      "losses": 1396,
      "max_score": 70.82103497731079,
      "measured_at": null,
      "min_score": 3.1304801359516308,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 3,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3934,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.6046549628759,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333334,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.674922707272515,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1305
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:xiaomi-mimo-v2-5-pro:1173fd470ce74d1d",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.2996388,
        "mean": 0.08320818615,
        "median": 0.048126608099999996,
        "min": 0.0057139812,
        "recorded_attempt_count": 28,
        "run_count": 16,
        "total": 1.3313309783999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 794,
      "eligibility_flag": false,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T12:52:57Z",
      "losses": 1265,
      "max_score": 68.29746038794151,
      "measured_at": null,
      "min_score": 4.615901320625215,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 3,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3146,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.5625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.40730558412735,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1087
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-6-luna:cefd28a14bc6fb2f",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 23,
        "cost_basis_counts": {
          "local_standard_estimate": 23
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.014153675,
        "mean": 0.0061271967391304345,
        "median": 0.0038602999999999997,
        "min": 0.00161355,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 23
        },
        "run_count": 23,
        "token_priced_attempt_count": 23,
        "total": 0.140925525
      },
      "codegen_evaluated_cells": 23,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 530,
      "eligibility_flag": false,
      "entry_count": 23,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 23,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-07"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:22:13Z",
      "losses": 924,
      "max_score": 76.68636345470857,
      "measured_at": null,
      "min_score": 10.200783051786512,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 2040,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.1802628419337,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.045028877183,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 586
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-7-max:73b0c0f94bcd24fa",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.12185499999999999,
        "mean": 0.05695140625,
        "median": 0.036751875,
        "min": 0.015285,
        "recorded_attempt_count": 24,
        "run_count": 16,
        "total": 0.9112225
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1060,
      "eligibility_flag": false,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:45Z",
      "losses": 1133,
      "max_score": 72.93190187054188,
      "measured_at": null,
      "min_score": 10.664384932466085,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3159,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 32.734592623814834,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 966
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-6-luna:2e545312142d8002",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.0377622,
        "mean": 0.01391661875,
        "median": 0.00586915,
        "min": 0.0040101,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 25
        },
        "run_count": 24,
        "token_priced_attempt_count": 25,
        "total": 0.33399884999999996
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2685,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 23,
      "first_pass_rate": 0.9583333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:41:54Z",
      "losses": 3268,
      "max_score": 81.2042772769244,
      "measured_at": null,
      "min_score": 8.701180641503443,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 8158,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.4917602993064,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 31.471409490295727,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2205
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-4-1:66990b9a341d522b",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.09459400000000001,
        "mean": 0.0571955,
        "median": 0.043012,
        "min": 0.032534,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 0.457564
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 620,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:23Z",
      "losses": 670,
      "max_score": 53.67468803008354,
      "measured_at": null,
      "min_score": 6.9862813021302,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1807,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.876939936900786,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 517
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:moonshotai-kimi-k2-7-code:0ddc5bc5de1cd512",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.226689264,
        "mean": 0.16037539425,
        "median": 0.140728509,
        "min": 0.10689655,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 1.2830031539999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 390,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-06"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:33:44Z",
      "losses": 458,
      "max_score": 51.93262612726081,
      "measured_at": null,
      "min_score": 10.785004751134416,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1358,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.600565633888362,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 510
    },
    {
      "admitted_plugins": 29,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:o3:bb9ab27740359998",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 29,
        "cell_count": 24,
        "cost_basis_counts": {
          "estimated": 40,
          "local_standard_estimate": 29
        },
        "cost_is_complete": false,
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 19,
        "max": 0.17217,
        "mean": 0.08358424999999998,
        "median": 0.0865375,
        "min": 0.037309999999999996,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 13,
          "boardgame-list-prices-2026-08-08": 16,
          "boardgame-list-prices-2026-09-08": 40
        },
        "recorded_attempt_count": 40,
        "run_count": 48,
        "token_priced_attempt_count": 29,
        "total": 4.2016860000000005
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1676,
      "eligibility_flag": false,
      "entry_count": 29,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-08"
      ],
      "first_pass_admitted": 29,
      "first_pass_rate": 0.6041666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:14:18Z",
      "losses": 5072,
      "max_score": 52.03780039623947,
      "measured_at": null,
      "min_score": 8.861174993521987,
      "model_code_failure_rate": 0.3958333333333333,
      "model_code_failures": 19,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 11010,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.6485338401678,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.520487489208833,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 4262
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:bytedance-seed-seed-2-0-code:38ab75f9172dbd13",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.075846,
        "mean": 0.041728458333333336,
        "median": 0.04202725,
        "min": 0.0121355,
        "recorded_attempt_count": 34,
        "run_count": 24,
        "total": 1.0014830000000001
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1792,
      "eligibility_flag": true,
      "entry_count": 22,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.5833333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:13:55Z",
      "losses": 2417,
      "max_score": 75.43253351935807,
      "measured_at": null,
      "min_score": 6.506552449736231,
      "model_code_failure_rate": 0.08333333333333333,
      "model_code_failures": 2,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5772,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.6497822848694,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 29.798693064342945,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1563
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-4-mini:597c0fcc8f6fc41d",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 17,
        "cost_basis_counts": {
          "estimated": 2,
          "local_standard_estimate": 22
        },
        "cost_is_complete": false,
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "max": 1.503294825,
        "mean": 0.2156185632352941,
        "median": 0.169101,
        "min": 0.01245825,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-08-08": 20,
          "boardgame-list-prices-2026-09-08": 2
        },
        "recorded_attempt_count": 2,
        "run_count": 18,
        "token_priced_attempt_count": 22,
        "total": 5.1688104
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 1258,
      "eligibility_flag": false,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.8125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:14:25Z",
      "losses": 1266,
      "max_score": 60.753181324378254,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3403,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 29.58072251616982,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 879
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-4-nano:5d223ef87df56f9e",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 17,
        "cost_basis_counts": {
          "estimated": 2,
          "local_standard_estimate": 55
        },
        "cost_is_complete": false,
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 8,
        "max": 0.26962149999999996,
        "mean": 0.03182758529411764,
        "median": 0.01676735,
        "min": 0.004854125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-08-08": 53,
          "boardgame-list-prices-2026-09-08": 2
        },
        "recorded_attempt_count": 2,
        "run_count": 34,
        "token_priced_attempt_count": 55,
        "total": 1.0821378999999998
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1238,
      "eligibility_flag": false,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-07"
      ],
      "first_pass_admitted": 10,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:41Z",
      "losses": 2297,
      "max_score": 57.82115624580523,
      "measured_at": null,
      "min_score": 10.4996181061563,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 8,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 5208,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 14,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 28.387812633883797,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1673
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:deepseek-deepseek-v4-flash:a1e016da344bef87",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 36,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 59
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.01423672,
        "mean": 0.004144189362222222,
        "median": 0.0032265161666666666,
        "min": 0.0008945895,
        "recorded_attempt_count": 59,
        "run_count": 40,
        "total": 0.16008749804000003
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2851,
      "eligibility_flag": true,
      "entry_count": 36,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-05"
      ],
      "first_pass_admitted": 20,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:26:54Z",
      "losses": 3679,
      "max_score": 79.88316261692358,
      "measured_at": null,
      "min_score": 9.347070314016047,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 4,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 8653,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.8207150341987,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 27.87648918191451,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2123
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:poolside-laguna-s-2-1:714c98e791307e1d",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 68
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.0068074,
        "mean": 0.0032179299999999995,
        "median": 0.00314426,
        "min": 0.0012446800000000002,
        "recorded_attempt_count": 68,
        "run_count": 28,
        "total": 0.09094181999999999
      },
      "codegen_evaluated_cells": 28,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2911,
      "eligibility_flag": false,
      "entry_count": 23,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 4,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:53Z",
      "losses": 3045,
      "max_score": 46.950499952815655,
      "measured_at": null,
      "min_score": 6.704785781203059,
      "model_code_failure_rate": 0.17857142857142858,
      "model_code_failures": 5,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 7609,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.32142857142857145,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 27.566070032428385,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1653
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:tencent-hy3-preview:fcc77a4d882226b3",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 25
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.007539277999999999,
        "mean": 0.0022565913437500003,
        "median": 0.0014932259999999998,
        "min": 0.00090937,
        "recorded_attempt_count": 25,
        "run_count": 17,
        "total": 0.041725613
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1062,
      "eligibility_flag": false,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5294117647058824,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T04:44:49Z",
      "losses": 1072,
      "max_score": 61.8142594407856,
      "measured_at": null,
      "min_score": 3.2968970313112287,
      "model_code_failure_rate": 0.23529411764705882,
      "model_code_failures": 4,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 2886,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 4,
      "repaired_rate": 0.23529411764705882,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 27.100724973200947,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 752
    },
    {
      "admitted_plugins": 43,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-5-flash-lite:a4a9549e62c079e1",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 43,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 132
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.0719635,
        "mean": 0.03858281041666666,
        "median": 0.037386975,
        "min": 0.012759,
        "recorded_attempt_count": 132,
        "run_count": 48,
        "total": 1.8519748999999996
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 5137,
      "eligibility_flag": true,
      "entry_count": 42,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-07"
      ],
      "first_pass_admitted": 36,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:00Z",
      "losses": 7555,
      "max_score": 56.66854839969095,
      "measured_at": null,
      "min_score": 8.198390781857146,
      "model_code_failure_rate": 0.10416666666666667,
      "model_code_failures": 5,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 16901,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.5600863094182,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 7,
      "repaired_rate": 0.14583333333333334,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 27.055334108396753,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 4209
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-7-plus:6637b5994cf7a3b7",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.08827968,
        "mean": 0.03155999,
        "median": 0.01479536,
        "min": 0.00524064,
        "recorded_attempt_count": 29,
        "run_count": 17,
        "total": 0.51646592
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 902,
      "eligibility_flag": false,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.29411764705882354,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:25:52Z",
      "losses": 1126,
      "max_score": 71.62538316070135,
      "measured_at": null,
      "min_score": 9.261021826492382,
      "model_code_failure_rate": 0.29411764705882354,
      "model_code_failures": 5,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 2707,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 7,
      "repaired_rate": 0.4117647058823529,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.88941841152139,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 679
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:x-ai-grok-build-0-1:32d67c2437a4ce5d",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.07439860000000001,
        "mean": 0.060660574999999994,
        "median": 0.0565846,
        "min": 0.0485456,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.48528460000000007
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 706,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:41:32Z",
      "losses": 739,
      "max_score": 50.969829451519225,
      "measured_at": null,
      "min_score": 12.067201319254902,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1874,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.302156667515924,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 429
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:meituan-longcat-2-0:c666de4f0835c2f6",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 26,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 108
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.103943664,
        "mean": 0.050012701874999996,
        "median": 0.041983026,
        "min": 0.006392298,
        "recorded_attempt_count": 108,
        "run_count": 32,
        "total": 1.60040646
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2289,
      "eligibility_flag": false,
      "entry_count": 26,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 17,
      "first_pass_rate": 0.53125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:14:18Z",
      "losses": 3709,
      "max_score": 41.60041525625513,
      "measured_at": null,
      "min_score": 7.685379769827811,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 6,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 7946,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.28125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.386317008942793,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1948
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:openai-gpt-oss-120b:64abe68ef22a237c",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.015120192000000001,
        "mean": 0.0032700552500000003,
        "median": 0.0013951725,
        "min": 0.00046744,
        "recorded_attempt_count": 33,
        "run_count": 24,
        "total": 0.078481326
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1913,
      "eligibility_flag": true,
      "entry_count": 21,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 16,
      "first_pass_rate": 0.6666666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:30Z",
      "losses": 2334,
      "max_score": 54.825621514346786,
      "measured_at": null,
      "min_score": 5.952533319730318,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 3,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5333,
      "rating_method": "sequential_elo",
      "raw_elo": 1324.1377675342821,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333334,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 24.920949595397968,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1086
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:stepfun-step-3-7-flash:a38a5f6eb512ab7e",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 59
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.11219570000000001,
        "mean": 0.0416694575,
        "median": 0.033877925,
        "min": 0.00984735,
        "recorded_attempt_count": 59,
        "run_count": 24,
        "total": 1.00006698
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 936,
      "eligibility_flag": false,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:08:15Z",
      "losses": 1857,
      "max_score": 48.401795904394994,
      "measured_at": null,
      "min_score": 11.348188198383951,
      "model_code_failure_rate": 0.4583333333333333,
      "model_code_failures": 11,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3769,
      "rating_method": "sequential_elo",
      "raw_elo": 1305.5568612242691,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 10,
      "repaired_rate": 0.4166666666666667,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 24.84296289334341,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 976
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:meta-muse-glimmer-30b:0d57fdf1ac4ff397",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.02351982,
        "mean": 0.011764807916666668,
        "median": 0.0084872,
        "min": 0.00402612,
        "recorded_attempt_count": 34,
        "run_count": 24,
        "total": 0.28235539000000004
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2118,
      "eligibility_flag": true,
      "entry_count": 21,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-06"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.5833333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:52:27Z",
      "losses": 2225,
      "max_score": 45.37253694835636,
      "measured_at": null,
      "min_score": 6.328311136424571,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 3,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5444,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.0816698635665,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 7,
      "repaired_rate": 0.2916666666666667,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 24.457685517154246,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1101
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemma-4-31b-it:055141364decf1b9",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 14,
        "cost_basis_counts": {
          "provider_reported": 23
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0092087,
        "mean": 0.004466478571428571,
        "median": 0.0042425399999999995,
        "min": 0.00144036,
        "recorded_attempt_count": 23,
        "run_count": 14,
        "total": 0.0625307
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 569,
      "eligibility_flag": false,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.35714285714285715,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality",
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:10:59Z",
      "losses": 1160,
      "max_score": 50.26394857772395,
      "measured_at": null,
      "min_score": 12.918261292629804,
      "model_code_failure_rate": 0.2857142857142857,
      "model_code_failures": 4,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 2322,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 5,
      "repaired_rate": 0.35714285714285715,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 24.03887590211112,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 593
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:thinkingmachines-inkling-small:0066eef0baf981d4",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 43
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.06806129999999999,
        "mean": 0.01775885625,
        "median": 0.0102184875,
        "min": 0.00430875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 43
        },
        "recorded_attempt_count": 43,
        "run_count": 28,
        "total": 0.5373185999999999
      },
      "codegen_evaluated_cells": 28,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2412,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 15,
      "first_pass_rate": 0.5357142857142857,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:11:37Z",
      "losses": 3001,
      "max_score": 57.00973194901733,
      "measured_at": null,
      "min_score": 4.881426142579081,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 4,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6749,
      "rating_method": "sequential_elo",
      "raw_elo": 1304.454703461232,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.32142857142857145,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.838365602331503,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1336
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:b9a2033385dc7bc1",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 70
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 13,
        "max": 0.13485595000000003,
        "mean": 0.03294963020833334,
        "median": 0.02851355,
        "min": 0.0111232,
        "recorded_attempt_count": 70,
        "run_count": 34,
        "total": 1.21164085
      },
      "codegen_evaluated_cells": 34,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1724,
      "eligibility_flag": false,
      "entry_count": 21,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.20588235294117646,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "untested_or_ineligible_settings"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T12:33:28Z",
      "losses": 1760,
      "max_score": 54.629833111248594,
      "measured_at": null,
      "min_score": 4.923730589416949,
      "model_code_failure_rate": 0.38235294117647056,
      "model_code_failures": 13,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 4337,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.1400544363503,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 14,
      "repaired_rate": 0.4117647058823529,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.492194258414813,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 853
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:minimax-minimax-m3:6106413b060d69af",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 30
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.09803328,
        "mean": 0.049222395,
        "median": 0.05336871,
        "min": 0.00639384,
        "recorded_attempt_count": 30,
        "run_count": 16,
        "total": 0.78755832
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 879,
      "eligibility_flag": false,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:19:38Z",
      "losses": 1392,
      "max_score": 42.47095379427678,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 3,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3016,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.5625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.2342990481235,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 745
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:xiaomi-mimo-v2-5:7ea22dc2e757d29f",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 37,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 108
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 16,
        "max": 0.0597184625,
        "mean": 0.015888486455555555,
        "median": 0.014928570933333333,
        "min": 0.00169122,
        "recorded_attempt_count": 108,
        "run_count": 56,
        "total": 0.7524538072000001
      },
      "codegen_evaluated_cells": 36,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2867,
      "eligibility_flag": false,
      "entry_count": 42,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.2222222222222222,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings"
      ],
      "infra_excluded_game_aliases": [
        "GB2-03",
        "GB2-06",
        "GB2-07"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:19:38Z",
      "losses": 3273,
      "max_score": 48.979799568566214,
      "measured_at": null,
      "min_score": 6.460914561290655,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 12,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 7840,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.8469275321356,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 16,
      "repaired_rate": 0.4444444444444444,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 22.87569332665649,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1700
    },
    {
      "admitted_plugins": 27,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:thinkingmachines-inkling:f3e37953cb77674a",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 27,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 145
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 21,
        "max": 0.302804525,
        "mean": 0.12502029041666668,
        "median": 0.082332765,
        "min": 0.01945095,
        "recorded_attempt_count": 145,
        "run_count": 48,
        "total": 6.00097394
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2641,
      "eligibility_flag": false,
      "entry_count": 27,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 16,
      "first_pass_rate": 0.3333333333333333,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:16:57Z",
      "losses": 3905,
      "max_score": 59.97193472120926,
      "measured_at": null,
      "min_score": 7.957773475504234,
      "model_code_failure_rate": 0.4375,
      "model_code_failures": 21,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 8362,
      "rating_method": "sequential_elo",
      "raw_elo": 1315.546167480228,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 11,
      "repaired_rate": 0.22916666666666666,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 22.76811532013747,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1816
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:mistralai-mistral-medium-3-5:d99706c7568df32b",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 16,
        "cost_basis_counts": {
          "local_list_price_estimate": 25
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.27741402547937455,
        "mean": 0.12115799999999999,
        "median": 0.10979066017348882,
        "min": 0.04290565490575157,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 25
        },
        "run_count": 16,
        "token_priced_attempt_count": 25,
        "total": 1.9385279999999996
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1330,
      "eligibility_flag": false,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-07"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.4375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:21:56Z",
      "losses": 1678,
      "max_score": 56.99034820792066,
      "measured_at": null,
      "min_score": 3.83400018350949,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3579,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 21.537725210435838,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 571
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:cohere-north-mini-code:bb91725eb139a0ce",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 45
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 13,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 45,
        "run_count": 24,
        "total": 0.0
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 755,
      "eligibility_flag": false,
      "entry_count": 17,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "unknown_capability_evidence",
        "missing_generation_quality",
        "below_generation_quality_threshold",
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:19:01Z",
      "losses": 1340,
      "max_score": 48.748765419591805,
      "measured_at": null,
      "min_score": 15.744039665353446,
      "model_code_failure_rate": 0.5416666666666666,
      "model_code_failures": 13,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 2594,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333334,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 21.051375112251986,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 499
    },
    {
      "admitted_plugins": 17,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:inception-mercury-2-5-preview:0488ec4b2b7f9fb1",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 17,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.0025894200000000003,
        "mean": 0.0011797070833333334,
        "median": 0.000945325,
        "min": 0.00044038,
        "recorded_attempt_count": 37,
        "run_count": 24,
        "total": 0.028312969999999996
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1867,
      "eligibility_flag": true,
      "entry_count": 17,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-05",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.5416666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:27:19Z",
      "losses": 2007,
      "max_score": 38.37213841472128,
      "measured_at": null,
      "min_score": 10.772886758516659,
      "model_code_failure_rate": 0.2916666666666667,
      "model_code_failures": 7,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4494,
      "rating_method": "sequential_elo",
      "raw_elo": 1324.762178916667,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 4,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 19.65786602912411,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 620
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:nex-agi-nex-n2-pro:80ab6d29e00cc243",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 12,
        "max": 0.215758025,
        "mean": 0.132049078125,
        "median": 0.1281735,
        "min": 0.061553000000000004,
        "recorded_attempt_count": 53,
        "run_count": 24,
        "total": 3.40579925
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 781,
      "eligibility_flag": false,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality",
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:53Z",
      "losses": 1324,
      "max_score": 64.55194498926986,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 12,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 2658,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 12,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 19.07367324525054,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 553
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-1-flash-lite:01d4f61c18cd57c6",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 50
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 8,
        "max": 0.0422995,
        "mean": 0.014503875,
        "median": 0.010566625,
        "min": 0.003432,
        "recorded_attempt_count": 50,
        "run_count": 24,
        "total": 0.34809300000000004
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 914,
      "eligibility_flag": false,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.20833333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "untested_or_ineligible_settings"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T12:16:54Z",
      "losses": 1993,
      "max_score": 32.38410669171022,
      "measured_at": null,
      "min_score": 0.08310002118024254,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 8,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3533,
      "rating_method": "sequential_elo",
      "raw_elo": 1030.3999332914716,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 11,
      "repaired_rate": 0.4583333333333333,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 16.956767089532573,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 626
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:inclusionai-ling-3-0-flash:4585443c22a6925f",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 92
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 15,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 92,
        "run_count": 32,
        "total": 0.0
      },
      "codegen_evaluated_cells": 31,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1867,
      "eligibility_flag": false,
      "entry_count": 22,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.22580645161290322,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "unknown_capability_evidence",
        "missing_generation_quality",
        "below_generation_quality_threshold",
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:59Z",
      "losses": 2320,
      "max_score": 38.44617773407611,
      "measured_at": null,
      "min_score": 2.780537548479402,
      "model_code_failure_rate": 0.4838709677419355,
      "model_code_failures": 15,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 5048,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.2903225806451613,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 16.802608996281997,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 861
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:ibm-granite-granite-4-2-8b:ebff985e112e2d67",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 3,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 54
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 21,
        "max": 0.010999479999999999,
        "mean": 0.004008075000000001,
        "median": 0.00280168,
        "min": 0.00126116,
        "recorded_attempt_count": 54,
        "run_count": 24,
        "total": 0.09619379999999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 69,
      "draws": 377,
      "eligibility_flag": false,
      "entry_count": 3,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "untested_or_ineligible_settings",
        "missing_generation_quality",
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:28:45Z",
      "losses": 403,
      "max_score": 22.686800313770597,
      "measured_at": null,
      "min_score": 0.7174978039660215,
      "model_code_failure_rate": 0.8125,
      "model_code_failures": 13,
      "model_display_name": "Granite 4.2 8B",
      "model_slug": "ibm-granite-granite-4-2-8b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 798,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 10.144355486455655,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 18
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1962,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-6-astra:dd3177afdee2bb2a",
      "capped_draws": 21,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.48718,
        "mean": 0.4090425,
        "median": 0.40659249999999997,
        "min": 0.311405,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-05": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 3.27234
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 81.66546467894545,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 204,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:19:37Z",
      "losses": 161,
      "max_score": 95.69162884853398,
      "measured_at": null,
      "min_score": 58.93727047228494,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1962,
      "rating_method": "sequential_elo",
      "raw_elo": 1995.377815650245,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 81.66546467894545,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1597
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1950,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-fable-5-1:6cd78ef6c83f1088",
      "capped_draws": 1,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 1.511677676840267,
        "mean": 1.1541937045345083,
        "median": 1.126127596791556,
        "min": 0.7961115304367101,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 9.233549636276067
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 75.04188072111677,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 161,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:05:54Z",
      "losses": 241,
      "max_score": 91.91733247569104,
      "measured_at": null,
      "min_score": 27.6720155573788,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1950,
      "rating_method": "sequential_elo",
      "raw_elo": 1946.0202078820396,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 75.04188072111677,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1548
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 814,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-opus-5-5:1dbe90fb38520c77",
      "capped_draws": 4,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.728964,
        "mean": 0.33381875,
        "median": 0.267474,
        "min": 0.167816,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 3.006308
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 74.49726125112892,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 26,
      "eligibility_flag": true,
      "entry_count": 9,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.8888888888888888,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:45Z",
      "losses": 61,
      "max_score": 81.57822709514194,
      "measured_at": null,
      "min_score": 69.8950709756612,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 814,
      "rating_method": "sequential_elo",
      "raw_elo": 1923.1468343541355,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 74.49726125112892,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 727
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2100,
      "canonical_public_row_identity": "publication-row.v1:balanced:z-ai-glm-5-3:ebf51d85881ca5b8",
      "capped_draws": 137,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.23469315999999998,
        "mean": 0.156944395,
        "median": 0.1664265,
        "min": 0.07192,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 1.25555516
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 60.37629544290532,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 377,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:30Z",
      "losses": 497,
      "max_score": 91.34449020371359,
      "measured_at": null,
      "min_score": 23.547509730974397,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2098,
      "rating_method": "sequential_elo",
      "raw_elo": 1763.5848588349686,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 60.37629544290532,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1224
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 2916,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 41,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.551725,
        "mean": 0.44617968750000003,
        "median": 0.45788,
        "min": 0.33828,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 7.1388750000000005
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 61.757649808905576,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 387,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:14:25Z",
      "losses": 485,
      "max_score": 82.13477554310234,
      "measured_at": null,
      "min_score": 15.978871709726342,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2914,
      "rating_method": "sequential_elo",
      "raw_elo": 1820.5481727667586,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 59.73003562775136,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 2042
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1938,
      "canonical_public_row_identity": "publication-row.v1:balanced:x-ai-grok-4-6:69246fd982959de2",
      "capped_draws": 70,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.179588,
        "mean": 0.12726625,
        "median": 0.12371399999999999,
        "min": 0.092184,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 1.01813
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 57.76474815367045,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 411,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:25:05Z",
      "losses": 451,
      "max_score": 78.05231532268954,
      "measured_at": null,
      "min_score": 24.805218937462044,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1932,
      "rating_method": "sequential_elo",
      "raw_elo": 1751.035141388364,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 57.76474815367045,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1070
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 720,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-6-sol:6603d35f27967aeb",
      "capped_draws": 18,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.1118895,
        "mean": 0.07831456249999999,
        "median": 0.0772785,
        "min": 0.0550535,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.6265165
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 57.34076897878964,
      "contributing_entrants": null,
      "distinct_rated_opponents": 67,
      "draws": 124,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:29:47Z",
      "losses": 144,
      "max_score": 78.85328563520711,
      "measured_at": null,
      "min_score": 31.714134573439228,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 720,
      "rating_method": "sequential_elo",
      "raw_elo": 1745.257481737596,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 57.34076897878964,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 452
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2638,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 139,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.24740375,
        "mean": 0.229063125,
        "median": 0.23243875,
        "min": 0.20046375,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.8325050000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 56.590178181129204,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 422,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:44Z",
      "losses": 729,
      "max_score": 74.92326063693565,
      "measured_at": null,
      "min_score": 36.36805948391099,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2636,
      "rating_method": "sequential_elo",
      "raw_elo": 1684.8387853717302,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 56.590178181129204,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1485
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2120,
      "canonical_public_row_identity": "publication-row.v1:balanced:z-ai-glm-5-3-flash:1cd9221832b4ca47",
      "capped_draws": 204,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.01518705,
        "mean": 0.00578608125,
        "median": 0.0045066875,
        "min": 0.0032555,
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.04628865
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 54.61401951813503,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 527,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:42:02Z",
      "losses": 647,
      "max_score": 73.9709651519967,
      "measured_at": null,
      "min_score": 19.58473584796164,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2113,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.7927997705892,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 54.61401951813503,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 939
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1966,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-fable-5:4fee988c3b8ad119",
      "capped_draws": 27,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.73774,
        "mean": 0.5233875,
        "median": 0.47084000000000004,
        "min": 0.34112,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.1871
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.2483566362053,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 383,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:33Z",
      "losses": 546,
      "max_score": 83.86890130218805,
      "measured_at": null,
      "min_score": 13.925660427832574,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1966,
      "rating_method": "sequential_elo",
      "raw_elo": 1702.2162215820367,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 53.2483566362053,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1037
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2106,
      "canonical_public_row_identity": "publication-row.v1:balanced:meta-muse-spark-1-3:b928c7e11b83bab6",
      "capped_draws": 18,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.07423675,
        "mean": 0.05217515625,
        "median": 0.050446875,
        "min": 0.04135875,
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.41740125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.63974829395818,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 321,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:27:19Z",
      "losses": 680,
      "max_score": 78.27779768942712,
      "measured_at": null,
      "min_score": 26.121442848759003,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2098,
      "rating_method": "sequential_elo",
      "raw_elo": 1654.5132916237949,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 50.63974829395818,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1097
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1808,
      "canonical_public_row_identity": "publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 17,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.0878628,
        "mean": 0.0635932,
        "median": 0.06199639999999999,
        "min": 0.0498884,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.5087455999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 48.89069299775914,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 425,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:30Z",
      "losses": 501,
      "max_score": 71.98011275701009,
      "measured_at": null,
      "min_score": 18.426880670928522,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1806,
      "rating_method": "sequential_elo",
      "raw_elo": 1636.9963976842268,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 48.89069299775914,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 880
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1920,
      "canonical_public_row_identity": "publication-row.v1:balanced:tencent-hy4-preview:a81918b0d5baba2a",
      "capped_draws": 19,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.190258393,
        "mean": 0.135826968,
        "median": 0.126875313,
        "min": 0.097439089,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 1.0866157440000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 49.77163099580157,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 310,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:11:51Z",
      "losses": 648,
      "max_score": 81.28231996103942,
      "measured_at": null,
      "min_score": 9.957083818816807,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": 0.875,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1919,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.2716358517375,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 48.13753926565109,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 961
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2208,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-8-flash:5a72b22afc48c9d2",
      "capped_draws": 348,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.061982706,
        "mean": 0.0376887,
        "median": 0.037827133,
        "min": 0.02582591,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.3015096
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.30415802742198,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 742,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:29:21Z",
      "losses": 579,
      "max_score": 74.00144873524822,
      "measured_at": null,
      "min_score": 24.898458456294655,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2207,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.6798664080998,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 47.30415802742198,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 886
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 688,
      "canonical_public_row_identity": "publication-row.v1:balanced:xiaomi-mimo-v2-6-flash:2cbc2b572299d3d2",
      "capped_draws": 66,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.02304638,
        "mean": 0.0178225775,
        "median": 0.01816367,
        "min": 0.01029504,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 11
        },
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.14258062
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.115778688864275,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 126,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:54Z",
      "losses": 212,
      "max_score": 73.64786897600108,
      "measured_at": null,
      "min_score": 20.29762262352045,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": 1.0,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 688,
      "rating_method": "sequential_elo",
      "raw_elo": 1605.2982547213696,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 47.115778688864275,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 350
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2162,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-8-flash:9fd2f22238c82925",
      "capped_draws": 221,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.12249677080183623,
        "mean": 0.07182689102312519,
        "median": 0.06440174762499168,
        "min": 0.044067488277453076,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.5746151281850016
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.04816057368627,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 650,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:52:47Z",
      "losses": 647,
      "max_score": 71.62237123829571,
      "measured_at": null,
      "min_score": 15.032375698995798,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2155,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.8947278491648,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 47.04816057368627,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 858
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2094,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-5-flash:099e26902a6430db",
      "capped_draws": 146,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 10
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.27117240812024124,
        "mean": 0.1983136265434789,
        "median": 0.18868274576048882,
        "min": 0.15676593388665558,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 1.5865090123478314
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 45.94264480977134,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 567,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:25:05Z",
      "losses": 693,
      "max_score": 70.75278873396961,
      "measured_at": null,
      "min_score": 12.815210820746566,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2093,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.139740546044,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 45.94264480977134,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 833
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2802,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 278,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.4120425,
        "mean": 0.283374375,
        "median": 0.26543625,
        "min": 0.2124125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 2.266995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.08690114479181,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 900,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:05:53Z",
      "losses": 780,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2796,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.5353596497243,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 44.08690114479181,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1116
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 4953,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 334,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 44
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.3888165,
        "mean": 0.26060548125,
        "median": 0.24728879999999998,
        "min": 0.17802225,
        "recorded_attempt_count": 44,
        "run_count": 16,
        "total": 4.1696877
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 45.26783194625648,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1154,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-08"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:33:39Z",
      "losses": 1421,
      "max_score": 77.04707674780836,
      "measured_at": null,
      "min_score": 7.58639288876681,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4951,
      "rating_method": "sequential_elo",
      "raw_elo": 1619.710091683987,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 43.7816080001001,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 2376
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2236,
      "canonical_public_row_identity": "publication-row.v1:balanced:deepseek-deepseek-v4-pro:768bc94990435e72",
      "capped_draws": 31,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.06923239834,
        "mean": 0.046577516286750005,
        "median": 0.0458058365,
        "min": 0.023862969,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.37262013029400004
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.259109027909574,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 471,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:36Z",
      "losses": 803,
      "max_score": 72.3322501482903,
      "measured_at": null,
      "min_score": 9.212833783417654,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2236,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.7045340306577,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 41.259109027909574,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 962
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 672,
      "canonical_public_row_identity": "publication-row.v1:balanced:deepseek-deepseek-v4-1-flash:3af710709a8e8646",
      "capped_draws": 85,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.0294003,
        "mean": 0.0190911675,
        "median": 0.019388559,
        "min": 0.011042118,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.15272934
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.942459007178655,
      "contributing_entrants": null,
      "distinct_rated_opponents": 69,
      "draws": 201,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:54Z",
      "losses": 192,
      "max_score": 71.98934050814864,
      "measured_at": null,
      "min_score": 12.331930401575923,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 672,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.501691629872,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 40.942459007178655,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 279
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 2531,
      "canonical_public_row_identity": "publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 97,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.060198249999999995,
        "mean": 0.047021,
        "median": 0.04824225,
        "min": 0.0324825,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.376168
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.15120052283497,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 621,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:53:18Z",
      "losses": 789,
      "max_score": 72.07963331402082,
      "measured_at": null,
      "min_score": 13.581319779736006,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": 0.875,
      "provider": "Other",
      "provider_key": "other",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2530,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.643988348296,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 40.767301164662655,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1120
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1636,
      "canonical_public_row_identity": "publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:64e1b98629aed328",
      "capped_draws": 198,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.2996388,
        "mean": 0.13471628689999998,
        "median": 0.1144847257,
        "min": 0.027613287599999998,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 1.0777302951999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.12357564467532,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 322,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:28:48Z",
      "losses": 644,
      "max_score": 68.29746038794151,
      "measured_at": null,
      "min_score": 19.252817076331517,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": 0.75,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1636,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.37788294831,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 39.200404177689705,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 670
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2272,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 172,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.25803,
        "mean": 0.104435,
        "median": 0.081263,
        "min": 0.075542,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.83548
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.04266865722575,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 695,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:44Z",
      "losses": 823,
      "max_score": 62.54041731185943,
      "measured_at": null,
      "min_score": 11.88308300278399,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2271,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.9949595759922,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 39.04266865722575,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 753
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 4878,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 355,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.266665,
        "mean": 0.20888499999999996,
        "median": 0.20905875000000002,
        "min": 0.14104,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 8,
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 3.3421600000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.90241887186665,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 807,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:03:41Z",
      "losses": 1195,
      "max_score": 66.84543135872292,
      "measured_at": null,
      "min_score": 9.818228255319736,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3324,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.8860705237812,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.90241887186665,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1322
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1734,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-5:21e993e2d5aeba11",
      "capped_draws": 258,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.58673,
        "mean": 0.44285687500000004,
        "median": 0.4176025,
        "min": 0.34269,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.542855
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.67245608046029,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 608,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:20:10Z",
      "losses": 494,
      "max_score": 72.713931668433,
      "measured_at": null,
      "min_score": 17.509396641546054,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1734,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.6062877027753,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.67245608046029,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 632
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1776,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-opus-4-8:4cb92d0ddc0c0f20",
      "capped_draws": 218,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.34174499999999997,
        "mean": 0.217940625,
        "median": 0.19638,
        "min": 0.14813,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.7435250000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.05563536159708,
      "contributing_entrants": null,
      "distinct_rated_opponents": 69,
      "draws": 668,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:52:48Z",
      "losses": 492,
      "max_score": 75.74725395578018,
      "measured_at": null,
      "min_score": 11.23707888740107,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1776,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.2826219719254,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.05563536159708,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 616
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3386,
      "canonical_public_row_identity": "publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 443,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.4398702,
        "mean": 0.29041619999999996,
        "median": 0.301782,
        "min": 0.095232,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 16
        },
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 2.3233296
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.00861893086849,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1162,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:08:02Z",
      "losses": 1162,
      "max_score": 61.60666625896725,
      "measured_at": null,
      "min_score": 12.829263374876211,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 1.0,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3376,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.6442603943458,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.00861893086849,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1052
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2266,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-terra:0fc18f792ad6d67d",
      "capped_draws": 96,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.146648125,
        "mean": 0.09696234375000001,
        "median": 0.09060875000000002,
        "min": 0.083821875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.7756987499999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.3173433619514,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 620,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:06Z",
      "losses": 866,
      "max_score": 62.7636226124865,
      "measured_at": null,
      "min_score": 13.179346281696866,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2266,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.6830664292281,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 37.3173433619514,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 780
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3658,
      "canonical_public_row_identity": "publication-row.v1:balanced:z-ai-glm-5-2:ce87a33d1a10c901",
      "capped_draws": 539,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 26
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.14635563000000001,
        "mean": 0.0939111476625,
        "median": 0.10304704349999999,
        "min": 0.032703412,
        "recorded_attempt_count": 26,
        "run_count": 16,
        "total": 1.5025783626
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.25084999448105,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1318,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:51Z",
      "losses": 1154,
      "max_score": 73.77006751900642,
      "measured_at": null,
      "min_score": 17.36870095915482,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3658,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.0143099629447,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 37.25084999448105,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1186
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1751,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4-mini:fe5868df24c7eb11",
      "capped_draws": 118,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.325659,
        "mean": 0.25189603125,
        "median": 0.25775625,
        "min": 0.169101,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 2.01516825
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.21858849121705,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 528,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:14:25Z",
      "losses": 565,
      "max_score": 60.753181324378254,
      "measured_at": null,
      "min_score": 9.242992989536942,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1749,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.7117053387162,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 37.21858849121705,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 656
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": 7127,
      "canonical_public_row_identity": "publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 470,
      "codegen_cost_usd": {
        "admitted_cell_count": 26,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 39,
        "run_count": 30,
        "total": 0.0
      },
      "codegen_evaluated_cells": 30,
      "conditional_success_score": 37.91520962417879,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1717,
      "eligibility_flag": true,
      "entry_count": 26,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-06"
      ],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.7,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:23Z",
      "losses": 2719,
      "max_score": 54.925489222319115,
      "measured_at": null,
      "min_score": 15.804848105037715,
      "model_code_failure_rate": 0.13333333333333333,
      "model_code_failures": 4,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": 0.8666666666666667,
      "provider": "Other",
      "provider_key": "other",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 7112,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.997412814324,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 36.582761420788586,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 2676
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 690,
      "canonical_public_row_identity": "publication-row.v1:balanced:z-ai-glm-5-3-flashx:02af860bd4bc6de7",
      "capped_draws": 39,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.039202100000000004,
        "mean": 0.026445697500000004,
        "median": 0.025158225,
        "min": 0.015228470000000001,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 11
        },
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.21156558
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.5572086512823,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 175,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:09Z",
      "losses": 267,
      "max_score": 63.73802956993577,
      "measured_at": null,
      "min_score": 7.080049745365206,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 690,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.995916003377,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 36.5572086512823,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 248
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2324,
      "canonical_public_row_identity": "publication-row.v1:balanced:deepseek-deepseek-v4-pro-0813:e2a09b34905fa7a8",
      "capped_draws": 322,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.18085216,
        "mean": 0.12355654023,
        "median": 0.14129957716,
        "min": 0.04648314,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.98845232184
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.03872592479018,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 657,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:05:54Z",
      "losses": 880,
      "max_score": 71.79125135121897,
      "measured_at": null,
      "min_score": 8.629972723433358,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2318,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.539778845137,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 36.03872592479018,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 781
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1406,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-7-plus:d9ff77c29c60491e",
      "capped_draws": 267,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.08827968,
        "mean": 0.05437612,
        "median": 0.0574344,
        "min": 0.00733824,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.43500895999999994
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.20400839484258,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 466,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:25:52Z",
      "losses": 482,
      "max_score": 71.62538316070135,
      "measured_at": null,
      "min_score": 10.977938094235043,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": 0.75,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1406,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.1821194799195,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.55283584941791,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 458
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3023,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 349,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.08884,
        "mean": 0.06562375000000001,
        "median": 0.062855,
        "min": 0.049908,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.52499
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.630660325327945,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 951,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:27:18Z",
      "losses": 1168,
      "max_score": 49.82748733223222,
      "measured_at": null,
      "min_score": 9.60693783512406,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3022,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.0863684237786,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.630660325327945,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 903
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1428,
      "canonical_public_row_identity": "publication-row.v1:balanced:o3:379b476f076f05cb",
      "capped_draws": 183,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.072978,
        "mean": 0.048872,
        "median": 0.046325000000000005,
        "min": 0.037309999999999996,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.390976
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.121648482195226,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 385,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:26:28Z",
      "losses": 519,
      "max_score": 51.966061908297576,
      "measured_at": null,
      "min_score": 8.861174993521987,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1428,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.033819955415,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.545586455410955,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 524
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1738,
      "canonical_public_row_identity": "publication-row.v1:balanced:bytedance-seed-seed-2-0-code:4f756096d2af64d1",
      "capped_draws": 52,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.071558,
        "mean": 0.053513000000000005,
        "median": 0.0517895,
        "min": 0.034152,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.42810399999999993
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.14408027758309,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 486,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-07"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:32Z",
      "losses": 658,
      "max_score": 75.43253351935807,
      "measured_at": null,
      "min_score": 9.226164992898436,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": 0.875,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1738,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.9016719443946,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.990237218869844,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 594
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 692,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-8-max-0902:8a00540801758a0c",
      "capped_draws": 60,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.278232,
        "mean": 0.1058585,
        "median": 0.088878,
        "min": 0.054514,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 10
        },
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.846868
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.83694392650825,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 193,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:53Z",
      "losses": 278,
      "max_score": 54.31161562786239,
      "measured_at": null,
      "min_score": 16.575926558583998,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 691,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.590692556971,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.83694392650825,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 220
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1478,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5:b12eee0aca0b39f6",
      "capped_draws": 188,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.21477374999999999,
        "mean": 0.17756265624999998,
        "median": 0.17285124999999998,
        "min": 0.1418975,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 1.4205012499999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.43999991037421,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 414,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:14:31Z",
      "losses": 548,
      "max_score": 59.58082426309626,
      "measured_at": null,
      "min_score": 15.08141203859531,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1478,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.5491445609678,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.30927307032606,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 516
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2302,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-8-2-4t-a95b:a41a9f6e42ee2b8f",
      "capped_draws": 325,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.17384630544122162,
        "mean": 0.10235142090592425,
        "median": 0.0851321236175097,
        "min": 0.07156210251142602,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.8188113672473941
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.29577520839935,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 851,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:14Z",
      "losses": 856,
      "max_score": 58.16040418419862,
      "measured_at": null,
      "min_score": 13.524183164803983,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2299,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.880784407659,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.29577520839935,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 592
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2851,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 309,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.011164349999999998,
        "mean": 0.00631805625,
        "median": 0.005847,
        "min": 0.00434295,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.05054444999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.903427472866106,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 953,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:41:54Z",
      "losses": 1091,
      "max_score": 55.929576936759275,
      "measured_at": null,
      "min_score": 16.646470580801548,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2850,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.7249486896628,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 32.903427472866106,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 806
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1660,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-7-max:7ae33688873d42a9",
      "capped_draws": 218,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.12185499999999999,
        "mean": 0.09110296875000001,
        "median": 0.09280125,
        "min": 0.0343775,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.72882375
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.82068922880934,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 588,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:45Z",
      "losses": 545,
      "max_score": 72.93190187054188,
      "measured_at": null,
      "min_score": 10.664384932466085,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": 0.875,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1659,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.884354127069,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 32.71029546692019,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 526
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 2678,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4-nano:fe41b3b08bed80e1",
      "capped_draws": 182,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.034210525000000006,
        "mean": 0.024715571875,
        "median": 0.0256067375,
        "min": 0.01676735,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 25
        },
        "run_count": 16,
        "token_priced_attempt_count": 25,
        "total": 0.3954491500000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 33.12559705121601,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 512,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:41Z",
      "losses": 1160,
      "max_score": 57.82115624580523,
      "measured_at": null,
      "min_score": 10.746700809550001,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2676,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.6241452114477,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.8268415765198,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 1004
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1358,
      "canonical_public_row_identity": "publication-row.v1:balanced:moonshotai-kimi-k2-7-code:c5a740a2bb2202e6",
      "capped_draws": 32,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.226689264,
        "mean": 0.16037539425,
        "median": 0.140728509,
        "min": 0.10689655,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 1.2830031539999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.88244772696924,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 390,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-06"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:27:20Z",
      "losses": 458,
      "max_score": 51.93262612726081,
      "measured_at": null,
      "min_score": 10.785004751134416,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": 0.75,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1358,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.0233446208615,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.600565633888362,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 510
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 708,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-6-luna:d08f8d120a6f613c",
      "capped_draws": 71,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.0044690500000000005,
        "mean": 0.0038361124999999998,
        "median": 0.0037657374999999996,
        "min": 0.00283105,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.0306889
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.12942170206434,
      "contributing_entrants": null,
      "distinct_rated_opponents": 66,
      "draws": 216,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:14Z",
      "losses": 344,
      "max_score": 49.2610359164719,
      "measured_at": null,
      "min_score": 11.808719043622077,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 708,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.811079496877,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.12942170206434,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 4926,
      "canonical_public_row_identity": "publication-row.v1:balanced:deepseek-deepseek-v4-flash:23183d74d990acfd",
      "capped_draws": 548,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 36
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.008042989573333334,
        "mean": 0.0037891845841666666,
        "median": 0.0032265161666666666,
        "min": 0.002126702,
        "recorded_attempt_count": 36,
        "run_count": 24,
        "total": 0.09094043001999999
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.778620882094394,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1596,
      "eligibility_flag": true,
      "entry_count": 22,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 10,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:08:41Z",
      "losses": 2118,
      "max_score": 37.56680586128569,
      "measured_at": null,
      "min_score": 9.347070314016047,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.875,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4923,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.5721537510567,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.8665990385216,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1209
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1874,
      "canonical_public_row_identity": "publication-row.v1:balanced:x-ai-grok-build-0-1:ff297ea2b087257e",
      "capped_draws": 239,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.07439860000000001,
        "mean": 0.060660574999999994,
        "median": 0.0565846,
        "min": 0.0485456,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.48528460000000007
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.302156667515924,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 706,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:01Z",
      "losses": 739,
      "max_score": 50.969829451519225,
      "measured_at": null,
      "min_score": 12.067201319254902,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1874,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.6055230564798,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.302156667515924,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 429
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 4814,
      "canonical_public_row_identity": "publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 348,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 70
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.103943664,
        "mean": 0.0866474535,
        "median": 0.088847748,
        "min": 0.062759676,
        "recorded_attempt_count": 70,
        "run_count": 16,
        "total": 1.386359256
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 26.99763459419179,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 1249,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:12Z",
      "losses": 2341,
      "max_score": 36.90268984079009,
      "measured_at": null,
      "min_score": 11.64843348541389,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4767,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.0830957420344,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.12412993761782,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 46,
      "wins": 1177
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 4607,
      "canonical_public_row_identity": "publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 729,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0068074,
        "mean": 0.0034371900000000006,
        "median": 0.00326368,
        "min": 0.00211404,
        "recorded_attempt_count": 35,
        "run_count": 14,
        "total": 0.04917796
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 26.434769750155958,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 1976,
      "eligibility_flag": true,
      "entry_count": 11,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-07"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:53Z",
      "losses": 1838,
      "max_score": 38.973297355450676,
      "measured_at": null,
      "min_score": 6.704785781203059,
      "model_code_failure_rate": 0.21428571428571427,
      "model_code_failures": 3,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": 0.7857142857142857,
      "provider": "Other",
      "provider_key": "other",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4607,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.9124788726533,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 4,
      "repaired_rate": 0.2857142857142857,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 24.88809720804685,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 793
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2058,
      "canonical_public_row_identity": "publication-row.v1:balanced:openai-gpt-oss-120b:8fc70fdaca40b3e0",
      "capped_draws": 256,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.00145295,
        "mean": 0.001135709125,
        "median": 0.001180259,
        "min": 0.00078534,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.009085673
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 23.257439814922698,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 742,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:01Z",
      "losses": 953,
      "max_score": 38.54712305704406,
      "measured_at": null,
      "min_score": 5.952533319730318,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2056,
      "rating_method": "sequential_elo",
      "raw_elo": 1297.8167190343195,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.257439814922698,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 361
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2292,
      "canonical_public_row_identity": "publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 273,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.01196465,
        "mean": 0.00854730625,
        "median": 0.008640199999999999,
        "min": 0.00555765,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 15
        },
        "recorded_attempt_count": 15,
        "run_count": 9,
        "total": 0.07763975
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 23.891737064640214,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 777,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.4444444444444444,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:11:37Z",
      "losses": 1072,
      "max_score": 57.00973194901733,
      "measured_at": null,
      "min_score": 4.881426142579081,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "Other",
      "provider_key": "other",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2292,
      "rating_method": "sequential_elo",
      "raw_elo": 1286.9588560856132,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 4,
      "repaired_rate": 0.4444444444444444,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.19848351335541,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 443
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1128,
      "canonical_public_row_identity": "publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:cb3f73a563b2cc95",
      "capped_draws": 218,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 21
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.065385,
        "mean": 0.03551179375,
        "median": 0.032728425,
        "min": 0.0200767,
        "recorded_attempt_count": 21,
        "run_count": 9,
        "total": 0.31772779999999995
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 26.716578014107217,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 416,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-05"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:05:04Z",
      "losses": 457,
      "max_score": 54.629833111248594,
      "measured_at": null,
      "min_score": 6.3532038338859245,
      "model_code_failure_rate": 0.4444444444444444,
      "model_code_failures": 4,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": 0.5555555555555556,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1128,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.9441498399137,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 5,
      "repaired_rate": 0.5555555555555556,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.065491033644633,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 255
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3352,
      "canonical_public_row_identity": "publication-row.v1:balanced:xiaomi-mimo-v2-5:2d4c0273a1a0067c",
      "capped_draws": 300,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 52
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.03062629,
        "mean": 0.020124273158333334,
        "median": 0.017895481666666668,
        "min": 0.012095886733333333,
        "recorded_attempt_count": 52,
        "run_count": 24,
        "total": 0.486187507
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 24.816161020658885,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1313,
      "eligibility_flag": true,
      "entry_count": 15,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.08333333333333333,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-03",
        "GB2-06",
        "GB2-07"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:55Z",
      "losses": 1338,
      "max_score": 35.53404787217864,
      "measured_at": null,
      "min_score": 11.528397600725828,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 4,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.6666666666666666,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3352,
      "rating_method": "sequential_elo",
      "raw_elo": 1308.1669600789542,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 7,
      "repaired_rate": 0.5833333333333334,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 22.4239328201719,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 701
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 5479,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 792,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 48
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0481474,
        "mean": 0.03800683125,
        "median": 0.037386975,
        "min": 0.02957195,
        "recorded_attempt_count": 48,
        "run_count": 16,
        "total": 0.6081093000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 22.738090266039418,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1872,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:29Z",
      "losses": 2656,
      "max_score": 38.59409823246796,
      "measured_at": null,
      "min_score": 12.559414245662259,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5468,
      "rating_method": "sequential_elo",
      "raw_elo": 1267.48924928716,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 21.99155806446691,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 940
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1968,
      "canonical_public_row_identity": "publication-row.v1:balanced:meta-muse-glimmer-30b:05ba243db4d890c1",
      "capped_draws": 270,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.0138593,
        "mean": 0.00832475125,
        "median": 0.006849235,
        "min": 0.00556902,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.06659801
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 21.350513794117806,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 767,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:24:59Z",
      "losses": 863,
      "max_score": 35.202863811457455,
      "measured_at": null,
      "min_score": 7.305194459653427,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1968,
      "rating_method": "sequential_elo",
      "raw_elo": 1260.1453336549228,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 21.350513794117806,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 338
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1436,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-1-flash-lite:5c5885dbd1316439",
      "capped_draws": 206,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0149315,
        "mean": 0.0101355,
        "median": 0.010566625,
        "min": 0.00402875,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 0.081084
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 20.300581815650165,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 371,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:59:57Z",
      "losses": 773,
      "max_score": 30.361355618251846,
      "measured_at": null,
      "min_score": 4.322931554682457,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1434,
      "rating_method": "sequential_elo",
      "raw_elo": 1179.1526666984132,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 18.891820080243768,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 290
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1660,
      "canonical_public_row_identity": "publication-row.v1:balanced:minimax-minimax-m3:b1d66682be51617c",
      "capped_draws": 215,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.09705768000000001,
        "mean": 0.0730637925,
        "median": 0.07051098,
        "min": 0.05225028,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.58451034
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 18.8178035929424,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 573,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:29:29Z",
      "losses": 791,
      "max_score": 41.673700863833744,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": 0.875,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1660,
      "rating_method": "sequential_elo",
      "raw_elo": 1220.7328187639591,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 7,
      "repaired_rate": 0.875,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 18.199981419636146,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 296
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1510,
      "canonical_public_row_identity": "publication-row.v1:balanced:inception-mercury-2-5-preview:6204f9f816b5cf60",
      "capped_draws": 212,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0025894200000000003,
        "mean": 0.0012652800000000001,
        "median": 0.000871045,
        "min": 0.00078866,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.010122240000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 19.06070636578836,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 602,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:27:19Z",
      "losses": 741,
      "max_score": 25.490331698828758,
      "measured_at": null,
      "min_score": 10.772886758516659,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1509,
      "rating_method": "sequential_elo",
      "raw_elo": 1223.0001983376926,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 17.73798596192097,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 166
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1116,
      "canonical_public_row_identity": "publication-row.v1:balanced:nex-agi-nex-n2-pro:c0da63af5f63c563",
      "capped_draws": 36,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.13491350000000002,
        "mean": 0.10247140625000001,
        "median": 0.113468875,
        "min": 0.061553000000000004,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.81977125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 19.1930133474309,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 120,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:53Z",
      "losses": 774,
      "max_score": 28.39953999096173,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": 0.625,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1116,
      "rating_method": "sequential_elo",
      "raw_elo": 1135.9672594066092,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 17.065270226169293,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 222
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 522,
      "canonical_public_row_identity": "publication-row.v1:balanced:x-ai-grok-4-7:2b9add2699eb467f",
      "capped_draws": 2,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 7
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.4355744,
        "mean": 0.2698891428571428,
        "median": 0.2679664,
        "min": 0.0,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 6
        },
        "recorded_attempt_count": 7,
        "run_count": 7,
        "total": 1.889224
      },
      "codegen_evaluated_cells": 6,
      "conditional_success_score": 67.44242954428366,
      "contributing_entrants": null,
      "distinct_rated_opponents": 69,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-06"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:53:32Z",
      "losses": 87,
      "max_score": 81.37689077370601,
      "measured_at": null,
      "min_score": 57.56745440692937,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 522,
      "rating_method": "sequential_elo",
      "raw_elo": 1843.029216297003,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 67.44242954428366,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 417
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 464,
      "canonical_public_row_identity": "publication-row.v1:balanced:xiaomi-mimo-v2-6-pro:fda4222fd76ceab7",
      "capped_draws": 16,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 5,
        "cost_basis_counts": {
          "provider_reported": 5
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.1085880432,
        "mean": 0.08096321663999999,
        "median": 0.07468254,
        "min": 0.048483795,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 5
        },
        "recorded_attempt_count": 5,
        "run_count": 5,
        "total": 0.4048160832
      },
      "codegen_evaluated_cells": 5,
      "conditional_success_score": 59.63173372243593,
      "contributing_entrants": null,
      "distinct_rated_opponents": 68,
      "draws": 108,
      "eligibility_flag": false,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:50Z",
      "losses": 51,
      "max_score": 77.84906750984048,
      "measured_at": null,
      "min_score": 39.83045327654045,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": 1.0,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 464,
      "rating_method": "sequential_elo",
      "raw_elo": 1772.8510959796026,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 59.63173372243593,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 305
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1516,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-8-27b:395c64922f7fe00a",
      "capped_draws": 151,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.079473456,
        "mean": 0.042855077875,
        "median": 0.0387132625,
        "min": 0.0,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.342840623
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 42.524861260861684,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 238,
      "eligibility_flag": false,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.2857142857142857,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:33:49Z",
      "losses": 700,
      "max_score": 57.945684696607124,
      "measured_at": null,
      "min_score": 25.78823504946214,
      "model_code_failure_rate": 0.2857142857142857,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": 0.7142857142857143,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1515,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.1938735317406,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 3,
      "repaired_rate": 0.42857142857142855,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 39.09407091889831,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 577
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 954,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemma-4-31b-it:3292f345f2f84049",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0092087,
        "mean": 0.006571171428571429,
        "median": 0.00666192,
        "min": 0.00456754,
        "recorded_attempt_count": 15,
        "run_count": 7,
        "total": 0.045998199999999996
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 30.60403246485289,
      "contributing_entrants": null,
      "distinct_rated_opponents": 67,
      "draws": 180,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-01"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:41:55Z",
      "losses": 475,
      "max_score": 50.26394857772395,
      "measured_at": null,
      "min_score": 19.990322662694933,
      "model_code_failure_rate": 0.42857142857142855,
      "model_code_failures": 3,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": 0.5714285714285714,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 952,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.5447305335833,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 4,
      "repaired_rate": 0.5714285714285714,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.60842335630734,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 297
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:balanced:cohere-north-mini-code:8bed39dcef9cf35b",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.0
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.324277808502853,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 405,
      "eligibility_flag": false,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:17:53Z",
      "losses": 666,
      "max_score": 48.748765419591805,
      "measured_at": null,
      "min_score": 16.125411079300658,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1402,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.2287033547227,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.358710559150524,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 331
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 950,
      "canonical_public_row_identity": "publication-row.v1:balanced:stepfun-step-3-7-flash:6a6c9f39d9a74010",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0711619,
        "mean": 0.039345212500000004,
        "median": 0.033877925,
        "min": 0.02387735,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.3147617
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 24.810268396923682,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 400,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:11:58Z",
      "losses": 370,
      "max_score": 48.401795904394994,
      "measured_at": null,
      "min_score": 11.348188198383951,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": 0.5,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 950,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.1533183661343,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 20.862865756455648,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 2157,
      "canonical_public_row_identity": "publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 394,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 10,
        "max": 0.11839474,
        "mean": 0.07845433000000002,
        "median": 0.08046371000000001,
        "min": 0.036046930000000005,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 1.25526928
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 23.298318032066064,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 706,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:17Z",
      "losses": 1039,
      "max_score": 41.59139577501191,
      "measured_at": null,
      "min_score": 7.957773475504234,
      "model_code_failure_rate": 0.625,
      "model_code_failures": 10,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.375,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 2154,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.022066402523,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 18.231919146815006,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 409
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:balanced:inclusionai-ling-3-0-flash:763a09e132a02aad",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 52
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 52,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": 21.516338854208463,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 706,
      "eligibility_flag": false,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.06666666666666667,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold",
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:34:04Z",
      "losses": 1299,
      "max_score": 38.44617773407611,
      "measured_at": null,
      "min_score": 2.780537548479402,
      "model_code_failure_rate": 0.6,
      "model_code_failures": 9,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": 0.4,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 2542,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.3355606204636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": 5,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 17.111314480985172,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 537
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 546,
      "canonical_public_row_identity": "publication-row.v1:balanced:ibm-granite-granite-4-2-8b:9c9c55a34daec5ca",
      "capped_draws": 199,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.00272269,
        "mean": 0.001801155,
        "median": 0.001648355,
        "min": 0.00126116,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 0.01440924
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 11.70214905886831,
      "contributing_entrants": null,
      "distinct_rated_opponents": 65,
      "draws": 199,
      "eligibility_flag": false,
      "entry_count": 2,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:28:45Z",
      "losses": 335,
      "max_score": 22.686800313770597,
      "measured_at": null,
      "min_score": 0.7174978039660215,
      "model_code_failure_rate": 0.75,
      "model_code_failures": 6,
      "model_display_name": "Granite 4.2 8B",
      "model_slug": "ibm-granite-granite-4-2-8b",
      "plugin_success_rate": 0.25,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 546,
      "rating_method": "sequential_elo",
      "raw_elo": 1053.0817840368368,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 8.274668953981557,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-09-25T05:26:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 2278.825931725217,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 307
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-5-5:1dbe90fb38520c77",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-09-25T12:46:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1914.6552626349105,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.31520041908865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 322,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-25T15:53:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 322,
      "rating_method": "sequential_elo",
      "raw_elo": 1889.1817125892937,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.07963331402082,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 250
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1895.2687657071344,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.98011275701009,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 141
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-5-flash:099e26902a6430db",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T14:08:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1816.8108855019566,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.59984810877775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:z-ai-glm-5-3-flash:1cd9221832b4ca47",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.3762702550496,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.06310136370395,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-fable-5-1:6cd78ef6c83f1088",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-22T12:52:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1793.818548037135,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.05633016038571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 182
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 650,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 256,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 230,
      "draws": 256,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 128,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 650,
      "rating_method": "sequential_elo",
      "raw_elo": 1781.376438319557,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 64.24089412492873,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 266
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:z-ai-glm-5-3-flashx:02af860bd4bc6de7",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.020483743773,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.73802956993577,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-6-terra:0fc18f792ad6d67d",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1762.4363561467956,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.7636226124865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 394,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:64e1b98629aed328",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 394,
      "rating_method": "sequential_elo",
      "raw_elo": 1747.7486728929528,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.09238331960013,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 230
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:x-ai-grok-4-7:2b9add2699eb467f",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T12:45:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1770.0444447829527,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.986006568145754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 357,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T14:08:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1742.1375362854433,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.60666625896725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:meta-muse-spark-1-3:b928c7e11b83bab6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-09-25T13:19:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1734.759712457236,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.756781153993344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 190,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-4-mini:fe5868df24c7eb11",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-09-25T12:46:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1738.0389555080314,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.753181324378254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-8-flash:9fd2f22238c82925",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-09-25T06:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1718.9045844132177,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.60452983725393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-6-astra:dd3177afdee2bb2a",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1709.169890183018,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.93727047228494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 370,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 152,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 370,
      "rating_method": "sequential_elo",
      "raw_elo": 1705.0749290256176,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.364791089349026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 236
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-fable-5:4fee988c3b8ad119",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-09-25T12:05:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1676.2121600864764,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.519674933057175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 634,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 122,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 267,
      "draws": 122,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 179,
      "max_score": null,
      "measured_at": "2026-09-25T04:53:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 634,
      "rating_method": "sequential_elo",
      "raw_elo": 1650.141425370019,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.925489222319115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 333
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T15:07:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.9125422305578,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.62351061515375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 144
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:deepseek-deepseek-v4-1-flash:3af710709a8e8646",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-09-25T07:56:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1641.1861002345797,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.44295115748309,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:z-ai-glm-5-3:ebf51d85881ca5b8",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T14:02:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.6235685063568,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.86956687787791,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-5:21e993e2d5aeba11",
      "capped_draws": 130,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 130,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T07:41:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.6577112125444,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.73139480630345,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 638,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 234,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 220,
      "draws": 136,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 133,
      "max_score": null,
      "measured_at": "2026-09-25T16:03:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 468,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.8885398034024,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.39151672846605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:deepseek-deepseek-v4-pro:768bc94990435e72",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.4251198887735,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.334139920659695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:x-ai-grok-4-6:69246fd982959de2",
      "capped_draws": 69,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.8054293883342,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.914921531324325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:bytedance-seed-seed-2-0-code:4f756096d2af64d1",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.2246491961014,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.99394925717289,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:xiaomi-mimo-v2-6-flash:2cbc2b572299d3d2",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T04:04:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.4873648676273,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.81148803602438,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 371,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 170,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 371,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.6692927335687,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.91146308402966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:deepseek-deepseek-v4-pro-0813:e2a09b34905fa7a8",
      "capped_draws": 202,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 202,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T04:38:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.1313317362046,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.02267217841239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:tencent-hy4-preview:a81918b0d5baba2a",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 141,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.2996642393953,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.61529521482249,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-7-plus:d9ff77c29c60491e",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.5348404139154,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.95850131307906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-8-2-4t-a95b:a41a9f6e42ee2b8f",
      "capped_draws": 110,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 110,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-09-25T07:41:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.8453959707654,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.34129805960164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 218,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-4-8:4cb92d0ddc0c0f20",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-22T15:56:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.627713228418,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.223782013343296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:cb3f73a563b2cc95",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-09-25T00:11:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.6138129385795,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.14634293665803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 332,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-8-flash:5a72b22afc48c9d2",
      "capped_draws": 121,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 143,
      "draws": 121,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 119,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 332,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.6065705765584,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.08673683836688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:xiaomi-mimo-v2-6-pro:fda4222fd76ceab7",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.5833168613892,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.83045327654045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-8-27b:395c64922f7fe00a",
      "capped_draws": 145,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 145,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-23T11:41:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.6059149220514,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.98414085011295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 464,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 146,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 230,
      "max_score": null,
      "measured_at": "2026-09-25T12:55:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 464,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.705955614129,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.973297355450676,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 111,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 111,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.1685015656856,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.84302075911713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 958,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 157,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 301,
      "draws": 157,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 470,
      "max_score": null,
      "measured_at": "2026-09-25T13:25:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 958,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.1572038478112,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.59409823246796,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 331
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 407,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 204,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 407,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.931270627249,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.892139986097995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 644,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:deepseek-deepseek-v4-flash:23183d74d990acfd",
      "capped_draws": 77,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 270,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 353,
      "max_score": null,
      "measured_at": "2026-09-25T14:13:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 642,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.4241530668423,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.27867614801619,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 212
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 420,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:z-ai-glm-5-2:ce87a33d1a10c901",
      "capped_draws": 170,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 174,
      "draws": 170,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 133,
      "max_score": null,
      "measured_at": "2026-09-25T12:45:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 420,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.6184657082804,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.792694938604896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:o3:379b476f076f05cb",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-09-25T02:20:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.0647950863756,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.707552632427934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-6-luna:d08f8d120a6f613c",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.9606199703867,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.2677047708935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:x-ai-grok-build-0-1:ff297ea2b087257e",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.8380320982249,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.18568291274274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:openai-gpt-oss-120b:8fc70fdaca40b3e0",
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 45,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 131,
      "max_score": null,
      "measured_at": "2026-09-25T06:24:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.5935344813565,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.899998911953496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-6-sol:6603d35f27967aeb",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.892434022501,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.84684899959481,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:c5a740a2bb2202e6",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.1626289780015,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.577592074565786,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-1-flash-lite:5c5885dbd1316439",
      "capped_draws": 123,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 123,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-09-24T06:12:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1310.2844110489343,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.361355618251846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:xiaomi-mimo-v2-5:2d4c0273a1a0067c",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 158,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 214,
      "max_score": null,
      "measured_at": "2026-09-25T15:53:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1309.2195945488988,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.060296329002895,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 117,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 117,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 182,
      "max_score": null,
      "measured_at": "2026-09-25T03:11:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.3053028064285,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.67228693230946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-8-max-0902:8a00540801758a0c",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1271.4328293956996,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.238232783733412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:meta-muse-glimmer-30b:05ba243db4d890c1",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 136,
      "max_score": null,
      "measured_at": "2026-09-25T07:14:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1208.4108885699306,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.0126853545906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:inclusionai-ling-3-0-flash:763a09e132a02aad",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 265,
      "max_score": null,
      "measured_at": "2026-09-25T13:39:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 386,
      "rating_method": "sequential_elo",
      "raw_elo": 1227.4780847101188,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.81526569038575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.54883454426297,
      "unilateral_faults": null,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:minimax-minimax-m3:b1d66682be51617c",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T04:00:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1170.1433865299655,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.07046347802326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5:b12eee0aca0b39f6",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1126.8105583111628,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.963732521903303,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-7-max:7ae33688873d42a9",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 120,
      "max_score": null,
      "measured_at": "2026-09-25T04:58:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1116.7667296118393,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.28451698383895,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-4-nano:fe41b3b08bed80e1",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 150,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 258,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1066.6378423386482,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.579978838993426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 208,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 954.7891752047293,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 4.881426142579081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-fable-5-1:6cd78ef6c83f1088",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-09-25T05:18:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1958.7340226504202,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.0713065691807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-opus-5-5:1dbe90fb38520c77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1907.3870916629003,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.78826057875526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-6-astra:dd3177afdee2bb2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1807.7572388878887,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.90856632210667,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 146
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:xiaomi-mimo-v2-6-pro:fda4222fd76ceab7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1737.3177663783688,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.95961453842323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 149,
      "draws": 154,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 395,
      "rating_method": "sequential_elo",
      "raw_elo": 1673.9642494443597,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.759035246055106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 215
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:xiaomi-mimo-v2-6-flash:2cbc2b572299d3d2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-09-25T06:53:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.2719135698069,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.622136291619164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 162,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T05:46:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.969068467395,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.36805948391099,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-fable-5:4fee988c3b8ad119",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 140,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1610.0612275564356,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.08336866932161,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-6-sol:6603d35f27967aeb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.9785633907034,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.714134573439228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 159,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.9709614984808,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.323646009270874,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:deepseek-deepseek-v4-1-flash:3af710709a8e8646",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-09-25T07:32:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.771308630353,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.34825360224334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:meta-muse-spark-1-3:b928c7e11b83bab6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 152,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T05:15:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.6620961166543,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.121442848759003,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-8-flash:5a72b22afc48c9d2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 157,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.3998389349945,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.898458456294655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:x-ai-grok-4-6:69246fd982959de2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 160,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.649227789607,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.805218937462044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:z-ai-glm-5-3:ebf51d85881ca5b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 163,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.1569523858368,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.547509730974397,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:z-ai-glm-5-3-flashx:02af860bd4bc6de7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.5919741849273,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.229397698507874,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:z-ai-glm-5-3-flash:1cd9221832b4ca47",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 185,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.8617465400573,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.58473584796164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 218,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-5:21e993e2d5aeba11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 142,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-18T19:19:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.1983241231044,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.212396895406123,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 462,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:z-ai-glm-5-2:ce87a33d1a10c901",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 186,
      "draws": 354,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 462,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.3398409819695,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.36870095915482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-6-terra:0fc18f792ad6d67d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 233,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.6676710089532,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.25920994124026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-8-max-0902:8a00540801758a0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.4873472445463,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.199228787720973,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 814,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 257,
      "draws": 721,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 91,
      "max_score": null,
      "measured_at": "2026-09-25T14:02:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 814,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.251491718369,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.857571915656177,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 297,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.298834098546,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.646470580801548,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-8-2-4t-a95b:a41a9f6e42ee2b8f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 204,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.1239013621373,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.550806400289524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 722,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 308,
      "draws": 549,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 98,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 722,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.8008998324374,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.804848105037715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 333,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 265,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 333,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.226429295739,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.152435531238186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:google-gemini-3-8-flash:9fd2f22238c82925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 225,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.09447306829,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.032375698995798,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 335,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 118,
      "draws": 252,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 335,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.0048383762835,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.581319779736006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-7-max:7ae33688873d42a9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 201,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.3219932683191,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.522719036613323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:c5a740a2bb2202e6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 193,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.4985349638378,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.984272900063827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 275,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.9628140050902,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.829263374876211,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 272,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:google-gemini-3-5-flash:099e26902a6430db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 226,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.9520788257767,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.815210820746566,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 409,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 361,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T14:34:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 409,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.6811806382134,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.559414245662259,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 232,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.8149010053573,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.465517805734288,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:x-ai-grok-build-0-1:ff297ea2b087257e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 220,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-24T19:00:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.1908067528893,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.067201319254902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:inception-mercury-2-5-preview:6204f9f816b5cf60",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 217,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.2021984898463,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.973977531323163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 280,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 232,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 280,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.9860199294324,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.88308300278399,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:openai-gpt-oss-120b:8fc70fdaca40b3e0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 208,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-09-25T05:15:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.1856422429778,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.830818971683568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-6-luna:d08f8d120a6f613c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.0091397204333,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.808719043622077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 129,
      "draws": 320,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.3376250866384,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.64843348541389,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 660,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:xiaomi-mimo-v2-5:2d4c0273a1a0067c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 236,
      "draws": 563,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 660,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.485031531869,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.528397600725828,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 582,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 199,
      "draws": 308,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.961299453459,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.50913920007812,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:stepfun-step-3-7-flash:6a6c9f39d9a74010",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 204,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.4189027911261,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.348188198383951,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-opus-4-8:4cb92d0ddc0c0f20",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 202,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.4106515911064,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.23707888740107,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-7-plus:d9ff77c29c60491e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.9764402657258,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.977938094235043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-4-nano:fe41b3b08bed80e1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 191,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.2084405501407,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.746700809550001,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:deepseek-deepseek-v4-pro-0813:e2a09b34905fa7a8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 176,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.736386569079,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.089425367998915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 340,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 285,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 340,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.6225297728333,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.60693783512406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 646,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:deepseek-deepseek-v4-flash:23183d74d990acfd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 245,
      "draws": 550,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 646,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.1169514798858,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.347070314016047,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-4-mini:fe5868df24c7eb11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 180,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T12:47:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.5307445622263,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.242992989536942,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:bytedance-seed-seed-2-0-code:4f756096d2af64d1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 208,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.6064511381016,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.226164992898436,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:deepseek-deepseek-v4-pro:768bc94990435e72",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T02:14:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.717879979862,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.212833783417654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:minimax-minimax-m3:b1d66682be51617c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 185,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.2500566846154,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.062637566537523,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.8860565669552,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.220985627441877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:cb3f73a563b2cc95",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 184,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T12:33:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.9560390913514,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.4721350280143835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:meta-muse-glimmer-30b:05ba243db4d890c1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 230,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T05:30:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.1719021757642,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.305194459653427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:inclusionai-ling-3-0-flash:763a09e132a02aad",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 8,
      "draws": 294,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.579899262466,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 2.780537548479402,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 38.75890625908325,
      "unilateral_faults": null,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-fable-5-1:6cd78ef6c83f1088",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-09-25T15:05:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1972.416702123303,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 82.02730182911166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 196
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-6-astra:dd3177afdee2bb2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T12:55:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1963.0600032369164,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.14783522356228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 159
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 125,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 297,
      "rating_method": "sequential_elo",
      "raw_elo": 1878.832615588344,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.60400026322671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 252
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-opus-5-5:1dbe90fb38520c77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1879.3579016389629,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.06960818323918,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-8-flash:9fd2f22238c82925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T15:52:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.5667967296579,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.42521343604795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 157
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:z-ai-glm-5-3:ebf51d85881ca5b8",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 223,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.032721767681,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.655310442580365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 146
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:x-ai-grok-4-7:2b9add2699eb467f",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T06:45:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1737.3085217737114,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.56745440692937,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:x-ai-grok-4-6:69246fd982959de2",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T05:08:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1703.2849728497006,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.698811869129386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:z-ai-glm-5-3-flash:1cd9221832b4ca47",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T07:24:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 235,
      "rating_method": "sequential_elo",
      "raw_elo": 1702.8455834195784,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.69463597353327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 104,
      "max_score": null,
      "measured_at": "2026-09-25T04:09:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 317,
      "rating_method": "sequential_elo",
      "raw_elo": 1670.9434445351742,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.03507393286738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 175
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-6-sol:6603d35f27967aeb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1686.2818549800577,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.69038122461175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 338,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 104,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-09-25T04:31:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 337,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.251265689971,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.17183438241479,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-5-flash:099e26902a6430db",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T13:06:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 227,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.1792080783332,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.096115949915344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.68086849439,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.508144083646044,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1829,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 61,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 7,
      "distinct_rated_opponents": 802,
      "draws": 332,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 669,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 1814,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.5361152807309,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.23380903288835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 813
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:qwen-qwen3-8-flash:5a72b22afc48c9d2",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 233,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.579881000369,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.1842635007645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:qwen-qwen3-8-max-0902:8a00540801758a0c",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T14:01:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.8608992836625,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.60300379005268,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 340,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-09-25T12:11:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 337,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.8806387963914,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.59139577501191,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:qwen-qwen3-8-27b:395c64922f7fe00a",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 319,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.817412312884,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.52872346510729,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T15:52:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.4368423578528,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.68914114822327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:deepseek-deepseek-v4-1-flash:3af710709a8e8646",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.9882420820213,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.11467185215879,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:xiaomi-mimo-v2-6-flash:2cbc2b572299d3d2",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T14:10:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.8354628199563,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.89535829138528,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 692,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 230,
      "draws": 146,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 301,
      "max_score": null,
      "measured_at": "2026-09-25T13:34:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 690,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.108182778877,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.68882139766329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 243
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:meta-muse-spark-1-3:b928c7e11b83bab6",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.4157889641933,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.22845180963232,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:z-ai-glm-5-3-flashx:02af860bd4bc6de7",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T14:01:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.789130216092,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.86266928865096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 115,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 137,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 379,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.0058603990226,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.73006163008332,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 486,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 182,
      "draws": 149,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-09-25T15:05:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 357,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.0595086507585,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.11276640129881,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:qwen-qwen3-8-2-4t-a95b:a41a9f6e42ee2b8f",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 146,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T04:36:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 311,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.7987684691807,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.16093776611165,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:deepseek-deepseek-v4-pro-0813:e2a09b34905fa7a8",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 48,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 159,
      "max_score": null,
      "measured_at": "2026-09-25T15:05:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.901306966007,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.898756018461224,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 107
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-6-luna:d08f8d120a6f613c",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.6104458381499,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.790788087810803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 161,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-4-mini:fe5868df24c7eb11",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 161,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.9895234122694,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.69551968181914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 378,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 165,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 125,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 377,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.2127966123949,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.60871326724313,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 372,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 188,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T15:05:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.4553692437319,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.602746818470994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 155,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.2724687641871,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.590881232571984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 367,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 135,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 144,
      "max_score": null,
      "measured_at": "2026-09-25T12:23:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 367,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.26332903877,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.399378159658458,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 816,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 268,
      "draws": 315,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 333,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 816,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.2676204995091,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.209728963258087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 168
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:tencent-hy4-preview:a81918b0d5baba2a",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 147,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T12:49:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 227,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.637968070786,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.716557872593558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 245,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 91,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 91,
      "max_score": null,
      "measured_at": "2026-09-25T04:46:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 245,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.3932195649575,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.03443283640638,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:deepseek-deepseek-v4-flash:23183d74d990acfd",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 151,
      "draws": 156,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 341,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.1241360082765,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.65635682627981,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.4376202060078436,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-opus-4-8:4cb92d0ddc0c0f20",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T15:52:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.9903528332513,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.38530689431558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:bytedance-seed-seed-2-0-code:4f756096d2af64d1",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 131,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.1997656077283,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.1673833049802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 701,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 232,
      "draws": 301,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 254,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 700,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.9246507141288,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.680993596380297,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:openai-gpt-oss-120b:8fc70fdaca40b3e0",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 96,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-09-25T14:01:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.1217167129957,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.640132783464484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:nex-agi-nex-n2-pro:c0da63af5f63c563",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.526619811048,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.81853039406397,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 358,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:z-ai-glm-5-2:ce87a33d1a10c901",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 153,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 358,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.0856388682455,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.44145855258766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-5:21e993e2d5aeba11",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.4651870198682,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.509396641546054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:meta-muse-glimmer-30b:05ba243db4d890c1",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1283.4809249094064,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.341929439664884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:x-ai-grok-build-0-1:ff297ea2b087257e",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T13:13:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1290.242440849019,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.32053682080132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-6-terra:0fc18f792ad6d67d",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 119,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T05:08:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1283.2051660127208,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.192155362935345,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 132,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5:b12eee0aca0b39f6",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T05:30:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1282.0012952043824,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.325386867061756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:cohere-north-mini-code:8bed39dcef9cf35b",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 10,
      "draws": 45,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1306.1751192514726,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.125411079300658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 32.6794725589981,
      "unilateral_faults": null,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-fable-5:4fee988c3b8ad119",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 142,
      "max_score": null,
      "measured_at": "2026-09-25T12:54:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1248.3349928557948,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.925660427832574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:deepseek-deepseek-v4-pro:768bc94990435e72",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-09-25T13:18:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1233.2156802078318,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.557760361514816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-6-astra:dd3177afdee2bb2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T13:06:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1961.1956366893105,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 95.69162884853398,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T15:33:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 311,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.4129004500003,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.23925278736691,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 208
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:z-ai-glm-5-3-flash:1cd9221832b4ca47",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-24T22:57:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.060755450437,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.92301827974818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 152
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-opus-5-5:1dbe90fb38520c77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1805.3403032296576,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.8950709756612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:z-ai-glm-5-3:ebf51d85881ca5b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 245,
      "rating_method": "sequential_elo",
      "raw_elo": 1783.7259066666843,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.04383353117605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 188
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:x-ai-grok-4-7:2b9add2699eb467f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1791.0168893205353,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.52073299307726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:xiaomi-mimo-v2-6-pro:fda4222fd76ceab7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1691.7277889611023,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.745857819297356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-6-sol:6603d35f27967aeb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T05:30:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1688.9460438675994,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.257540853318176,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:xiaomi-mimo-v2-6-flash:2cbc2b572299d3d2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.517725810686,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.35844545212433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:x-ai-grok-4-6:69246fd982959de2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 99,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.3811214442503,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.93009393174424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemini-3-8-flash:9fd2f22238c82925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 155,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-25T06:45:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.4731006614738,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.71773602229773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:meta-muse-spark-1-3:b928c7e11b83bab6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 100,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.6391068559133,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.67974117462816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemini-3-5-flash:099e26902a6430db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 132,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.0629310889913,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.351623972760336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:qwen-qwen3-8-flash:5a72b22afc48c9d2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 154,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T06:45:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.878576748059,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.57117101283803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-4-nano:fe41b3b08bed80e1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 121,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.4178925941112,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.558055123630105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:z-ai-glm-5-3-flashx:02af860bd4bc6de7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.8372344019856,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.002702443895366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 207,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.447010417425,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.499312490995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 762,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 312,
      "draws": 399,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 166,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 762,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.7841618976643,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.904976519441306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 197
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-fable-5-1:6cd78ef6c83f1088",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 107,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.3418830394744,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.6720155573788,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-fable-5:4fee988c3b8ad119",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 127,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-09-25T07:49:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.571534971346,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.320051355957688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:64e1b98629aed328",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 122,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.002911542282,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.703543197148946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-4-mini:fe5868df24c7eb11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 142,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.7428807986598,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.02215444542085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 444,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:z-ai-glm-5-2:ce87a33d1a10c901",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 165,
      "draws": 259,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 444,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.1221922986085,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.404154835140126,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 322,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 186,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 322,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.2184540066644,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.758731660036542,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-5:21e993e2d5aeba11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 149,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-09-25T07:32:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.6023650157663,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.354567805952815,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:meta-muse-glimmer-30b:05ba243db4d890c1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 185,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.097484815574,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.956344911843157,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-6-luna:d08f8d120a6f613c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.212853956462,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.377750187081375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemma-4-31b-it:3292f345f2f84049",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 180,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T04:44:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.2757496518636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.990322662694933,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:deepseek-deepseek-v4-pro:768bc94990435e72",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 169,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.1220332328212,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.91598677885711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 349,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.5444548730766,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.525005417352162,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 173,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.7623936685657,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.426880670928522,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:inception-mercury-2-5-preview:6204f9f816b5cf60",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 171,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 231,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.390731050095,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.16135373748405,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 615,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 210,
      "draws": 458,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 605,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.018220570183,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.810416612074924,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:stepfun-step-3-7-flash:6a6c9f39d9a74010",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 192,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.6781418918763,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.707558680335882,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 439,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 305,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 435,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.9772585746641,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.209086808065273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:qwen-qwen3-8-max-0902:8a00540801758a0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 81,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.798694413226,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.575926558583998,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.465763037423269,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-opus-4-8:4cb92d0ddc0c0f20",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 175,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.8785480714125,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.531176212156833,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemini-3-1-flash-lite:5c5885dbd1316439",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 164,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.2297377289594,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.41547033342719,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:cohere-north-mini-code:8bed39dcef9cf35b",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 24,
      "draws": 173,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.1308032078118,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.308603127079742,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.839285714285717,
      "unilateral_faults": null,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:x-ai-grok-build-0-1:ff297ea2b087257e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 194,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T06:12:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.5652326310567,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.267449298158713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 456,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 162,
      "draws": 187,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 153,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 456,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.1064001968423,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.978871709726342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 751,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 240,
      "draws": 418,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 221,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 705,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.459024040264,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.298717008537093,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 46,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5:b12eee0aca0b39f6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 154,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.5988635252065,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.08141203859531,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:bytedance-seed-seed-2-0-code:4f756096d2af64d1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 173,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0389380006973,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.045013366680111,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 310,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 178,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 310,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.5004246962953,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.189855510586924,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 200,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-24T19:26:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 277,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.687398706827,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.567734790878136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:qwen-qwen3-8-2-4t-a95b:a41a9f6e42ee2b8f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 166,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.2823151197556,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.524183164803983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 634,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:xiaomi-mimo-v2-5:2d4c0273a1a0067c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 234,
      "draws": 439,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 634,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.837514261648,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.182482558250914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-6-terra:0fc18f792ad6d67d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 147,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-09-25T06:30:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.179558951564,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.179346281696866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 496,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:deepseek-deepseek-v4-flash:23183d74d990acfd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 198,
      "draws": 359,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 496,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.158037374963,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.10783027783285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:deepseek-deepseek-v4-1-flash:3af710709a8e8646",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T13:06:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.8959541468055,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.331930401575923,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:inclusionai-ling-3-0-flash:763a09e132a02aad",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 21,
      "draws": 307,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T15:34:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 402,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.1586600442279,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.520265373967671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.249642583151164,
      "unilateral_faults": null,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:c5a740a2bb2202e6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 165,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.9282390844303,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.785004751134416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:qwen-qwen3-7-max:7ae33688873d42a9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 146,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 235,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.5002555098133,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.664384932466085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:tencent-hy4-preview:a81918b0d5baba2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 140,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.4433122904995,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.957083818816807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 416,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 159,
      "draws": 168,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 223,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.5828599891702,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.818228255319736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:minimax-minimax-m3:b1d66682be51617c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 172,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.7572226694713,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.720348794092118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:o3:379b476f076f05cb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 180,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.834382821887,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.861174993521987,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:deepseek-deepseek-v4-pro-0813:e2a09b34905fa7a8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.967405873055,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.629972723433358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 332,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 261,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 332,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.4511988255103,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.957773475504234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 603,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 205,
      "draws": 415,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T15:33:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 603,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.366983327068,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.58639288876681,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 384,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 238,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 384,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.6162527706854,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.704785781203059,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:openai-gpt-oss-120b:8fc70fdaca40b3e0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 96,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.7129756772986,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 5.952533319730318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 158,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.7909588152809,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-6-astra:dd3177afdee2bb2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 2081.47250029206,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.8365396088125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 211
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-fable-5-1:6cd78ef6c83f1088",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T07:02:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 2079.132350592878,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.69649309071661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 207
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 410,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 170,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 410,
      "rating_method": "sequential_elo",
      "raw_elo": 2024.0282553062893,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 82.13477554310234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 363
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:x-ai-grok-4-7:2b9add2699eb467f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 2028.0093303656413,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.37689077370601,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:x-ai-grok-4-6:69246fd982959de2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1957.513704268975,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 78.05231532268954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 187
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-6-sol:6603d35f27967aeb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T05:16:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1952.0875485730328,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.69079262608564,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1904.2282775886874,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.92326063693565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 239
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-5:21e993e2d5aeba11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1877.3036719014776,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.713931668433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-opus-5-5:1dbe90fb38520c77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1853.5470877597693,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.45502164921955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:z-ai-glm-5-3:ebf51d85881ca5b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 98,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1814.0769167802891,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.04748335935413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 142
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-fable-5:4fee988c3b8ad119",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.9643555457678,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.74309410747507,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 156
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemini-3-5-flash:099e26902a6430db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 98,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.5179187609167,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.70860889776725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1771.050242288496,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.53681950526628,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 218
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 820,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 279,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 246,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 820,
      "rating_method": "sequential_elo",
      "raw_elo": 1762.7376902370997,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.19105183427483,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 574
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-8-flash:5a72b22afc48c9d2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 82,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1725.532483239105,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.47838487808565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1727.6211599463707,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.4401888214157,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 97,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1710.8512444146102,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.54041731185943,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 190,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5:b12eee0aca0b39f6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-25T05:48:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.6221882023112,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.499000328638054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-6-terra:0fc18f792ad6d67d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 125,
      "max_score": null,
      "measured_at": "2026-09-25T05:01:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1643.4520137846655,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.44890987380218,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-8-2-4t-a95b:a41a9f6e42ee2b8f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 155,
      "max_score": null,
      "measured_at": "2026-09-25T12:53:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1637.5421322613147,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.16040418419862,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:z-ai-glm-5-3-flash:1cd9221832b4ca47",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 171,
      "max_score": null,
      "measured_at": "2026-09-25T15:42:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.9190358488256,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.90420106515226,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-7-plus:d9ff77c29c60491e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.7502453944767,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.62022193946525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 121
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:xiaomi-mimo-v2-6-flash:2cbc2b572299d3d2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.6238144120402,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.34370347170291,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:meta-muse-spark-1-3:b928c7e11b83bab6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.9576519998002,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.832172172826105,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:deepseek-deepseek-v4-pro:768bc94990435e72",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 153,
      "max_score": null,
      "measured_at": "2026-09-25T12:27:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.5191377924639,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.4262704810341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 490,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:z-ai-glm-5-2:ce87a33d1a10c901",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 200,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 232,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 490,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.0079400312711,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.641190570473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 258
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 474,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 146,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 213,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 474,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.9996058964011,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.57759582487964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 261
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:tencent-hy4-preview:a81918b0d5baba2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 150,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.0068505036463,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.05961783013132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 166
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:c5a740a2bb2202e6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T06:00:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.7377882000017,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.93262612726081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:x-ai-grok-build-0-1:ff297ea2b087257e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.6673413728931,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.969829451519225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemma-4-31b-it:3292f345f2f84049",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.0078875378504,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.26394857772395,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:o3:379b476f076f05cb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.9103472929748,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.94772634864385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 414,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 146,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 206,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 414,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.9507083566857,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.90440468938342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 208
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:deepseek-deepseek-v4-1-flash:3af710709a8e8646",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.6932663496493,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.89140451614368,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 129,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 196,
      "max_score": null,
      "measured_at": "2026-09-25T03:35:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.5866413784245,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.82748733223222,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 184
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:bytedance-seed-seed-2-0-code:4f756096d2af64d1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T03:31:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.392215434343,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.641747320730154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-6-luna:d08f8d120a6f613c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T13:28:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.543125364701,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.2610359164719,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 790,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 337,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 412,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 790,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.0060953819218,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.95613725220298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 378
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:cohere-north-mini-code:8bed39dcef9cf35b",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.6920140889088,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.748765419591805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.667361089076305,
      "unilateral_faults": null,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemini-3-8-flash:9fd2f22238c82925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 122,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.1599487804237,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.69228506640679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 112
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-4-mini:fe5868df24c7eb11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 92,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.6265842785156,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.57592667595412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 414,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-4-nano:fe41b3b08bed80e1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 153,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 198,
      "max_score": null,
      "measured_at": "2026-09-25T12:48:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 414,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.8605390108578,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.43969869217212,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 216
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:stepfun-step-3-7-flash:6a6c9f39d9a74010",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 117,
      "max_score": null,
      "measured_at": "2026-09-25T12:53:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.23979240712,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.401795904394994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-8-27b:395c64922f7fe00a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3666111185962,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.37752224301888,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 146
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-opus-4-8:4cb92d0ddc0c0f20",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T05:00:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.663742536622,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.23196258690973,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:deepseek-deepseek-v4-pro-0813:e2a09b34905fa7a8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 116,
      "max_score": null,
      "measured_at": "2026-09-25T05:32:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.8185414839636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.51115385299343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 152
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 636,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 222,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 215,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 450,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.3770803514549,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.26630148184913,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 235
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-8-max-0902:8a00540801758a0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.8335327503344,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.26930512569967,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-7-max:7ae33688873d42a9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.5900684076817,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.42220503142851,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 313,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 154,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 313,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.740228490143,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.275479635114195,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 159
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 825,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 260,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 543,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 825,
      "rating_method": "sequential_elo",
      "raw_elo": 1325.7183885846332,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.67815533375288,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 282
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 674,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:deepseek-deepseek-v4-flash:23183d74d990acfd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 279,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 413,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 674,
      "rating_method": "sequential_elo",
      "raw_elo": 1314.5396769568247,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.56680586128569,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 261
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 828,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 260,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 503,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 828,
      "rating_method": "sequential_elo",
      "raw_elo": 1297.5060696205567,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.90268984079009,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 325
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:z-ai-glm-5-3-flashx:02af860bd4bc6de7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.9295466118283,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.723346411404776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 446,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:xiaomi-mimo-v2-5:2d4c0273a1a0067c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 164,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 261,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 446,
      "rating_method": "sequential_elo",
      "raw_elo": 1282.8542233064363,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.53404787217864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:64e1b98629aed328",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 143,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1271.5826941372475,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.79835154781813,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemini-3-1-flash-lite:5c5885dbd1316439",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 144,
      "max_score": null,
      "measured_at": "2026-09-25T05:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1091.2531945362703,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.38472503344923,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 171,
      "max_score": null,
      "measured_at": "2026-09-23T03:27:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1086.0713160839841,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.21045764633968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:openai-gpt-oss-120b:8fc70fdaca40b3e0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 199,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1080.1171427813263,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.848650743910238,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:inception-mercury-2-5-preview:6204f9f816b5cf60",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 211,
      "max_score": null,
      "measured_at": "2026-09-25T04:36:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1077.15087262024,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.711376551122164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 768,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 245,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 623,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 768,
      "rating_method": "sequential_elo",
      "raw_elo": 1059.0605185213187,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.841650392139822,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:nex-agi-nex-n2-pro:c0da63af5f63c563",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 162,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1047.7461247257522,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.687011705599502,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:meta-muse-glimmer-30b:05ba243db4d890c1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 177,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1040.810738244802,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.281804865949653,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 205,
      "max_score": null,
      "measured_at": "2026-09-25T05:48:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1001.7884429744031,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.86158687607802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:minimax-minimax-m3:b1d66682be51617c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 248,
      "max_score": null,
      "measured_at": "2026-09-25T05:52:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 716.9732845937543,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:z-ai-glm-5-3:ebf51d85881ca5b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-09-25T05:06:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 2174.6692101629533,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 91.34449020371359,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 230
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-6-astra:dd3177afdee2bb2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T05:13:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 2070.4006161095167,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.03489742391993,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 210
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-fable-5-1:6cd78ef6c83f1088",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T06:44:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 2016.1486653040506,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.7142763946855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 193
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:meta-muse-spark-1-3:b928c7e11b83bab6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-24T23:38:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1958.2333885274027,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 78.27779768942712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-opus-5-5:1dbe90fb38520c77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-09-25T12:27:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1959.1974935170713,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.35850943307017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 786,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 256,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 786,
      "rating_method": "sequential_elo",
      "raw_elo": 1933.1562045476744,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.04707674780836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 611
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:xiaomi-mimo-v2-6-pro:fda4222fd76ceab7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1932.532829336563,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.77367546807812,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-opus-4-8:4cb92d0ddc0c0f20",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T05:26:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1919.2834556174316,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.74725395578018,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 173
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-fable-5:4fee988c3b8ad119",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1903.2394730829708,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.90758169037487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 174
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:x-ai-grok-4-6:69246fd982959de2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1897.9680555231073,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.56969734908822,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-8-flash:5a72b22afc48c9d2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1887.0566314718924,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.00144873524822,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:z-ai-glm-5-3-flash:1cd9221832b4ca47",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1887.5237166831148,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 73.9709651519967,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 336,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-25T03:04:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 336,
      "rating_method": "sequential_elo",
      "raw_elo": 1881.963566228328,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 73.85631875502746,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 249
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 482,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:z-ai-glm-5-2:ce87a33d1a10c901",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 191,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 98,
      "max_score": null,
      "measured_at": "2026-09-25T04:55:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 482,
      "rating_method": "sequential_elo",
      "raw_elo": 1884.5188350448484,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 73.77006751900642,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 360
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:deepseek-deepseek-v4-1-flash:3af710709a8e8646",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1870.302600353424,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.98934050814864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-7-plus:d9ff77c29c60491e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-24T21:34:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1849.9042563122262,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.62538316070135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemini-3-8-flash:9fd2f22238c82925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-09-25T03:04:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1848.7427852132082,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.62237123829571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 173
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemini-3-5-flash:099e26902a6430db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1834.450451701581,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.75278873396961,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-6-sol:6603d35f27967aeb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1829.9362462808288,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.64945689149215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:64e1b98629aed328",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-09-25T01:18:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1793.4876526516734,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.29746038794151,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:tencent-hy4-preview:a81918b0d5baba2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 141,
      "max_score": null,
      "measured_at": "2026-09-25T14:36:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.9656968929207,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.58021342324713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 193
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:xiaomi-mimo-v2-6-flash:2cbc2b572299d3d2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1653.5720186416438,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.94960636853664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 348,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-8-27b:395c64922f7fe00a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 145,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 151,
      "max_score": null,
      "measured_at": "2026-09-25T00:36:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 348,
      "rating_method": "sequential_elo",
      "raw_elo": 1618.1605396285938,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.945684696607124,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 478,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-4-nano:fe41b3b08bed80e1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 169,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 174,
      "max_score": null,
      "measured_at": "2026-09-25T01:00:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 478,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.5154003824932,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.82115624580523,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 286
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-7-max:7ae33688873d42a9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1602.9709274369272,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.7454811145915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 128
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 412,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 162,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 411,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.0758348930235,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.929576936759275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 232
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 492,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 157,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 204,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.7774959551684,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.86613972193045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 245
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:cb3f73a563b2cc95",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T07:48:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1568.3989131462947,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.629833111248594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 128
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-8-max-0902:8a00540801758a0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.059466017882,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.31161562786239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 162,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.9072035200847,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.92778094014556,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5:b12eee0aca0b39f6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 96,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.290841930129,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.28851664089777,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:z-ai-glm-5-3-flashx:02af860bd4bc6de7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.5273787833557,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.11749746309352,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-4-mini:fe5868df24c7eb11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.6696003044897,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.9350548600679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 124
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:o3:379b476f076f05cb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-09-25T05:06:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.4237574789388,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.543105104646564,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 348,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 184,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 348,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.6403620647127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.921635612672766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 158
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 330,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:deepseek-deepseek-v4-pro:768bc94990435e72",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 169,
      "max_score": null,
      "measured_at": "2026-09-25T05:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 330,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.9149423027568,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.903521988412955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 156
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 718,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 228,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 228,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 506,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.885554594425,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.85471815151569,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 237
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 340,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 169,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 340,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.5099746623619,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.992692305851016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 152,
      "max_score": null,
      "measured_at": "2026-09-25T12:47:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.2944605339005,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.187462067298945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 338,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-6-terra:0fc18f792ad6d67d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 139,
      "draws": 28,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 193,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 338,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.4045000243977,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.59328944547627,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-8-2-4t-a95b:a41a9f6e42ee2b8f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 150,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.4439636276202,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.84626674582942,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:x-ai-grok-build-0-1:ff297ea2b087257e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 150,
      "max_score": null,
      "measured_at": "2026-09-25T05:43:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.862610827383,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.09731404389463,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:deepseek-deepseek-v4-pro-0813:e2a09b34905fa7a8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 179,
      "max_score": null,
      "measured_at": "2026-09-25T04:48:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.4627200228902,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.053752059801255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:openai-gpt-oss-120b:8fc70fdaca40b3e0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 151,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.558641338468,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.54712305704406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 742,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:deepseek-deepseek-v4-flash:23183d74d990acfd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 291,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 470,
      "max_score": null,
      "measured_at": "2026-09-25T15:08:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 742,
      "rating_method": "sequential_elo",
      "raw_elo": 1234.6135842573058,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.56862070317807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 265
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-6-luna:d08f8d120a6f613c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1239.8605732376068,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.96181958467115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 810,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 253,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 541,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 810,
      "rating_method": "sequential_elo",
      "raw_elo": 1191.8149950533534,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.2888894086943,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 222
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:inclusionai-ling-3-0-flash:763a09e132a02aad",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 23,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 328,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 432,
      "rating_method": "sequential_elo",
      "raw_elo": 1206.8396642184798,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.0194479241334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.591247874473638,
      "unilateral_faults": null,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:cohere-north-mini-code:8bed39dcef9cf35b",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 171,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1200.7278853564226,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.499648290466038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.834993123162105,
      "unilateral_faults": null,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 620,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 244,
      "draws": 28,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 421,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 620,
      "rating_method": "sequential_elo",
      "raw_elo": 1156.6289503283863,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.979339503978853,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-5:21e993e2d5aeba11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 187,
      "max_score": null,
      "measured_at": "2026-09-24T15:30:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1150.2999734403245,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.53417748662991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 422,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 302,
      "max_score": null,
      "measured_at": "2026-09-25T15:10:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 422,
      "rating_method": "sequential_elo",
      "raw_elo": 1144.6544348969242,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.464909991973933,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:xiaomi-mimo-v2-5:2d4c0273a1a0067c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 165,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1148.1864008170126,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.3094167434742,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:minimax-minimax-m3:b1d66682be51617c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 164,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1105.2901358809513,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.7057657786473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemini-3-1-flash-lite:5c5885dbd1316439",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 166,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1094.304139623621,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.048639403495315,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:inception-mercury-2-5-preview:6204f9f816b5cf60",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 188,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1081.047870568292,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.25431191745537,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 259,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 202,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 259,
      "rating_method": "sequential_elo",
      "raw_elo": 1068.216179133427,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.524475172908698,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:bytedance-seed-seed-2-0-code:4f756096d2af64d1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 195,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1068.6933279372302,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.50177018126175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:nex-agi-nex-n2-pro:c0da63af5f63c563",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 190,
      "max_score": null,
      "measured_at": "2026-09-18T18:42:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1061.3788853371843,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.059984646529276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemma-4-31b-it:3292f345f2f84049",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 177,
      "max_score": null,
      "measured_at": "2026-09-25T14:10:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1049.0332225783065,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.30140252649068,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:meta-muse-glimmer-30b:05ba243db4d890c1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 199,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1041.1249118223438,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.879468141442242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:stepfun-step-3-7-flash:6a6c9f39d9a74010",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 197,
      "max_score": null,
      "measured_at": "2026-09-25T05:03:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1023.2764363744144,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.783530804579915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 790,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 247,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 659,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 790,
      "rating_method": "sequential_elo",
      "raw_elo": 943.9992522361157,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.306065189421517,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 284,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-6-astra:dd3177afdee2bb2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-23T10:05:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 2213.9870048414227,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 94.95689897734873,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 275
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-fable-5-1:6cd78ef6c83f1088",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T05:08:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 2169.7960624345815,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 91.91733247569104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 242
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-opus-5-5:1dbe90fb38520c77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 2030.8784144609388,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.57822709514194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 472,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 178,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T15:14:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 472,
      "rating_method": "sequential_elo",
      "raw_elo": 2015.2147642946993,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.48022089997005,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 405
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-6-sol:6603d35f27967aeb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T05:43:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1990.2209917943844,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 78.85328563520711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:xiaomi-mimo-v2-6-flash:2cbc2b572299d3d2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1915.2366881308399,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 73.64786897600108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-7-max:7ae33688873d42a9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T12:17:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1887.874488266294,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.93190187054188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 196
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:deepseek-deepseek-v4-pro-0813:e2a09b34905fa7a8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1868.5979423021952,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.79125135121897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 200
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:tencent-hy4-preview:a81918b0d5baba2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T04:36:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1860.3495757977012,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.19032884996027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 280,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-8-flash:5a72b22afc48c9d2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-09-22T13:00:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 280,
      "rating_method": "sequential_elo",
      "raw_elo": 1838.4946857611073,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.77939307553763,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:x-ai-grok-4-6:69246fd982959de2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1837.9987970990019,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.68601350315085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:z-ai-glm-5-3-flash:1cd9221832b4ca47",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T05:18:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1816.0959356058881,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.19200834208425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 175
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 370,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 370,
      "rating_method": "sequential_elo",
      "raw_elo": 1800.2013496000136,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.42033275926899,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 271
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:z-ai-glm-5-3:ebf51d85881ca5b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1799.0069770627845,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.07902568340647,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 183
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-fable-5:4fee988c3b8ad119",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1792.3257562370536,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.61852060343541,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-opus-4-8:4cb92d0ddc0c0f20",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1779.0511817326906,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.71581777847483,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:deepseek-deepseek-v4-pro:768bc94990435e72",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1774.4914466514606,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.39010876108995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:x-ai-grok-4-7:2b9add2699eb467f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1767.6454148188684,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 64.10825307420451,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:deepseek-deepseek-v4-1-flash:3af710709a8e8646",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1716.5424355001617,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.51080360289881,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-5:21e993e2d5aeba11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1696.2581746078608,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.08939481420384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 163
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5:b12eee0aca0b39f6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1687.9165793259276,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.58082426309626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 169
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 374,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 125,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 374,
      "rating_method": "sequential_elo",
      "raw_elo": 1675.240369774397,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.05264202522787,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 228
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 377,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 146,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 163,
      "max_score": null,
      "measured_at": "2026-09-22T14:30:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 377,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.67704856788,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.00973194901733,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 214
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 512,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:z-ai-glm-5-2:ce87a33d1a10c901",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 186,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 208,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 512,
      "rating_method": "sequential_elo",
      "raw_elo": 1648.0406863345377,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.93627466574622,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 304
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 364,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemini-3-8-flash:9fd2f22238c82925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 148,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 164,
      "max_score": null,
      "measured_at": "2026-09-25T12:49:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1627.8857977812459,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.860008031893024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 200
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-6-terra:0fc18f792ad6d67d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 122,
      "max_score": null,
      "measured_at": "2026-09-25T02:54:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.6449502469552,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.59577102591772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 144
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.2940888111907,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.55982608465452,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 358,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemini-3-5-flash:099e26902a6430db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 152,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 358,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.9642439877327,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.904620380720125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 206
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:o3:379b476f076f05cb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.3007031258494,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.966061908297576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 152
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:z-ai-glm-5-3-flashx:02af860bd4bc6de7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T05:32:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.1370577997548,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.703976589404945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-4-mini:fe5868df24c7eb11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-25T15:14:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.4570672951763,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.994068196362356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:meta-muse-spark-1-3:b928c7e11b83bab6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 155,
      "max_score": null,
      "measured_at": "2026-09-25T02:54:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.883430442997,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.07302698639267,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 752,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 238,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 294,
      "max_score": null,
      "measured_at": "2026-09-25T15:41:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 518,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.6761238799647,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.42124939768273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 224
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 434,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 144,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 211,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 434,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.3950796409993,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.82465145654429,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 223
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 766,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 251,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 361,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 766,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.9401740719447,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.52282307590832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 405
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:64e1b98629aed328",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 175,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.8861416519917,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.59689833921164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-8-max-0902:8a00540801758a0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.8170161899664,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.58541659334441,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-6-luna:d08f8d120a6f613c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.3198602798677,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.43933485308878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 858,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 365,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 471,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 858,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.68078832153,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.38360964767335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 387
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:c5a740a2bb2202e6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.3985733716686,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.77833026164878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:minimax-minimax-m3:b1d66682be51617c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 120,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.5301665145182,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.673700863833744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:inclusionai-ling-3-0-flash:763a09e132a02aad",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 565,
      "max_score": null,
      "measured_at": "2026-09-25T13:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 950,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.6214948670254,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.44617773407611,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.709041527651344,
      "unilateral_faults": null,
      "wins": 385
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 160,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.9282549861598,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.20183371033238,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 132
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 846,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 264,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 525,
      "max_score": null,
      "measured_at": "2026-09-25T12:53:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 846,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.7340905811943,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.04461312474943,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 321
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-8-2-4t-a95b:a41a9f6e42ee2b8f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 158,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.015355771146,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.2366026851926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 124
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:meta-muse-glimmer-30b:05ba243db4d890c1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 136,
      "max_score": null,
      "measured_at": "2026-09-25T13:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.882208334911,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.202863811457455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 130,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 227,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.602479274004,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.69185025593699,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:cohere-north-mini-code:8bed39dcef9cf35b",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 185,
      "max_score": null,
      "measured_at": "2026-09-23T01:36:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1325.7235521183766,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.45222425187841,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.622039417435602,
      "unilateral_faults": null,
      "wins": 113
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 660,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:deepseek-deepseek-v4-flash:23183d74d990acfd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 258,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 402,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 660,
      "rating_method": "sequential_elo",
      "raw_elo": 1287.0720177178437,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.643306070184295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 258
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 492,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-4-nano:fe41b3b08bed80e1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 179,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 306,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1280.7711885492126,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.29308716542273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 186
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 346,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 230,
      "max_score": null,
      "measured_at": "2026-09-25T15:41:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 346,
      "rating_method": "sequential_elo",
      "raw_elo": 1248.0929858646862,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.369602140205416,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 412,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 287,
      "max_score": null,
      "measured_at": "2026-09-25T07:49:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 412,
      "rating_method": "sequential_elo",
      "raw_elo": 1243.0906169640273,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.15433037896266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 474,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:xiaomi-mimo-v2-5:2d4c0273a1a0067c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 176,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 286,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 474,
      "rating_method": "sequential_elo",
      "raw_elo": 1246.7684906280847,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.97891004726828,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemma-4-31b-it:3292f345f2f84049",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 166,
      "max_score": null,
      "measured_at": "2026-09-25T15:41:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1228.862062366313,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.86045609250197,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:nex-agi-nex-n2-pro:c0da63af5f63c563",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 164,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1221.9849749023533,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.39953999096173,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 404,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 298,
      "max_score": null,
      "measured_at": "2026-09-25T06:31:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 404,
      "rating_method": "sequential_elo",
      "raw_elo": 1179.55633657311,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.883171168825367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 106
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-8-27b:395c64922f7fe00a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 125,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 237,
      "max_score": null,
      "measured_at": "2026-09-24T22:58:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1181.0188896765776,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.78823504946214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:openai-gpt-oss-120b:8fc70fdaca40b3e0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 193,
      "max_score": null,
      "measured_at": "2026-09-25T04:40:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1168.020631803829,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.78906384912377,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 274,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-7-plus:d9ff77c29c60491e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 183,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1153.9213565009122,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.88057228629806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:x-ai-grok-build-0-1:ff297ea2b087257e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 205,
      "max_score": null,
      "measured_at": "2026-09-25T06:31:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 994.9203420266373,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.187537598700027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 398,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 341,
      "max_score": null,
      "measured_at": "2026-09-25T05:08:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 398,
      "rating_method": "sequential_elo",
      "raw_elo": 979.2771944650718,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.450085377829959,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:inception-mercury-2-5-preview:6204f9f816b5cf60",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 235,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 958.6159767874869,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.772886758516659,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:cb3f73a563b2cc95",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 210,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 893.9437869150827,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.3532038338859245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemini-3-1-flash-lite:5c5885dbd1316439",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 212,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 864.0842697939028,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 4.322931554682457,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 272,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:ibm-granite-granite-4-2-8b:9c9c55a34daec5ca",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 260,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Granite 4.2 8B",
      "model_slug": "ibm-granite-granite-4-2-8b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 808.4054617383549,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.7174978039660215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-6-astra:dd3177afdee2bb2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 2155.9796349618264,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 87.81008055499466,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 241
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 286,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-fable-5:4fee988c3b8ad119",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 2103.0202723204475,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 83.86890130218805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 264
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:tencent-hy4-preview:a81918b0d5baba2a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T04:18:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 2070.1983831672133,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.28231996103942,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 230
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-fable-5-1:6cd78ef6c83f1088",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-23T01:57:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 2067.7734288744737,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.17998969178421,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 251
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:xiaomi-mimo-v2-6-pro:fda4222fd76ceab7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T04:49:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 2038.093778360589,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.84906750984048,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-opus-5-5:1dbe90fb38520c77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T12:23:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 2034.8111199288733,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.51819167485543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.051644180248918,
      "unilateral_faults": 0,
      "wins": 200
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 514,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 180,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T06:20:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 514,
      "rating_method": "sequential_elo",
      "raw_elo": 2013.6159955111561,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.98185391090948,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 455
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:bytedance-seed-seed-2-0-code:4f756096d2af64d1",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T04:00:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1993.1563562965605,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.43253351935807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 214
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:deepseek-deepseek-v4-pro:768bc94990435e72",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T13:41:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1952.230032189293,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.3322501482903,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 219
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:x-ai-grok-4-7:2b9add2699eb467f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T15:53:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1964.1506967203081,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.09523944963898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1941.3225089503185,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.51828642327122,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 233
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:x-ai-grok-4-6:69246fd982959de2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1927.6798227439356,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.46091278477508,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 205
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 650,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 88,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 221,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 422,
      "rating_method": "sequential_elo",
      "raw_elo": 1874.6575974676157,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.84543135872292,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 323
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 284,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:meta-muse-spark-1-3:b928c7e11b83bab6",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1856.555157626162,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.14857251600664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 200
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-6-sol:6603d35f27967aeb",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1856.7161709916622,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 64.02371102656826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 67,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1754.109003622718,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.64460987325958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 217
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1686.6240042460931,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.520486710806374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 226
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:z-ai-glm-5-3:ebf51d85881ca5b8",
      "capped_draws": 85,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 85,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-09-24T22:25:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1687.3866173471636,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.42314371415959,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 158
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1668.7501849907474,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.86933465904327,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:c5a740a2bb2202e6",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.4143031272313,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.23686024714184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 360,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 68,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 113,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 360,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.402338037299,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.19029962085715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 490,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4-nano:fe41b3b08bed80e1",
      "capped_draws": 128,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 167,
      "draws": 128,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 167,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 490,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.9577130546695,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.44050248293845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 912,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 287,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 385,
      "draws": 287,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 303,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 912,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.4008661019027,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.13346770988864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 322
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-5:21e993e2d5aeba11",
      "capped_draws": 121,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 121,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.0648943012557,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.23438852520712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:deepseek-deepseek-v4-pro-0813:e2a09b34905fa7a8",
      "capped_draws": 119,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 119,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.7025958077024,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.3128238460019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 451,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 261,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 261,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 120,
      "max_score": null,
      "measured_at": "2026-09-23T04:52:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 451,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.3679003269972,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.85503829239455,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 722,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:deepseek-deepseek-v4-flash:23183d74d990acfd",
      "capped_draws": 447,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 274,
      "draws": 447,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 179,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 722,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.528673146514,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.06030085596221,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 310,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-terra:0fc18f792ad6d67d",
      "capped_draws": 91,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 133,
      "draws": 91,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 310,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.4743152577723,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.506442352056098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 440,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 254,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 152,
      "draws": 254,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-09-25T07:31:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 440,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.0905055647788,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.766163938918144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 354,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-8-flash:5a72b22afc48c9d2",
      "capped_draws": 224,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 143,
      "draws": 224,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 92,
      "max_score": null,
      "measured_at": "2026-09-22T12:36:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 354,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.8902635327127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.43340772224031,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 286,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:o3:379b476f076f05cb",
      "capped_draws": 146,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 146,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-09-25T06:53:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.6689339264644,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.704269905633453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-8-max-0902:8a00540801758a0c",
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.4357551604487,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.912822145068468,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 835,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 299,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 261,
      "draws": 299,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 382,
      "max_score": null,
      "measured_at": "2026-09-25T14:38:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 835,
      "rating_method": "sequential_elo",
      "raw_elo": 1352.5170691998403,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.191386023914582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 548,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 376,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 164,
      "draws": 376,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 144,
      "max_score": null,
      "measured_at": "2026-09-25T01:53:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 548,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.9574897840018,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.65403469685162,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:z-ai-glm-5-3-flash:1cd9221832b4ca47",
      "capped_draws": 197,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 197,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.6593543617612,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.579490120899948,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-8-2-4t-a95b:a41a9f6e42ee2b8f",
      "capped_draws": 200,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 200,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.9944426793504,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.545702661167372,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4-mini:fe5868df24c7eb11",
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 95,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 107,
      "max_score": null,
      "measured_at": "2026-09-25T13:41:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.6382865503635,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.529809756196794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 280,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:openai-gpt-oss-120b:8fc70fdaca40b3e0",
      "capped_draws": 187,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 187,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T07:31:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 280,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.223467236304,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.55119688247162,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:inception-mercury-2-5-preview:6204f9f816b5cf60",
      "capped_draws": 212,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 212,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.5935405101955,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.490331698828758,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 882,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 616,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 280,
      "draws": 616,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 229,
      "max_score": null,
      "measured_at": "2026-09-25T13:41:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 882,
      "rating_method": "sequential_elo",
      "raw_elo": 1325.1732080243237,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.154938909796876,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:cb3f73a563b2cc95",
      "capped_draws": 179,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 179,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-25T05:23:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.808197108261,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.98137516072915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 479,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 266,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 150,
      "draws": 266,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 177,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 479,
      "rating_method": "sequential_elo",
      "raw_elo": 1321.1467474377516,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.907908985401132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 363,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 229,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 151,
      "draws": 229,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-09-25T13:01:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 363,
      "rating_method": "sequential_elo",
      "raw_elo": 1319.773428227486,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.597994074361377,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:minimax-minimax-m3:b1d66682be51617c",
      "capped_draws": 204,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 204,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-22T22:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1321.1854784744369,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.49170866946286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 338,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-8-flash:9fd2f22238c82925",
      "capped_draws": 190,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 190,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 128,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 338,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.3303361458036,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.43076525829919,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:x-ai-grok-build-0-1:ff297ea2b087257e",
      "capped_draws": 190,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 190,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T13:41:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1319.5573778937342,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.3217018950558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 834,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 586,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 255,
      "draws": 586,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 211,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 834,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.516631196398,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.228912691343204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-7-max:7ae33688873d42a9",
      "capped_draws": 158,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 158,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.166016388608,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.17361563218513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-7-plus:d9ff77c29c60491e",
      "capped_draws": 225,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 225,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T13:41:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.0055779922611,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.161433575276742,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 498,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:xiaomi-mimo-v2-5:2d4c0273a1a0067c",
      "capped_draws": 251,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 180,
      "draws": 251,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 191,
      "max_score": null,
      "measured_at": "2026-09-25T04:28:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 498,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.8174654587317,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.11957599371145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:meta-muse-glimmer-30b:05ba243db4d890c1",
      "capped_draws": 197,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 197,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.1836103666499,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.82381936834102,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5:b12eee0aca0b39f6",
      "capped_draws": 159,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 159,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1307.6036854276551,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.341126712427066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 237,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 237,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.9500960874611,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.215459853296952,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:cohere-north-mini-code:8bed39dcef9cf35b",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 26,
      "draws": 184,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-09-25T05:43:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.9228461053442,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.811014682700467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.465140987172258,
      "unilateral_faults": null,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 274,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:ibm-granite-granite-4-2-8b:9c9c55a34daec5ca",
      "capped_draws": 199,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 199,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Granite 4.2 8B",
      "model_slug": "ibm-granite-granite-4-2-8b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1297.7581063353189,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.686800313770597,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-opus-4-8:4cb92d0ddc0c0f20",
      "capped_draws": 160,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 160,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 85,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1294.3553301644727,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.372704564395118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-1-flash-lite:5c5885dbd1316439",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T06:15:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1278.7602474587914,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.27036895059496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 490,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:z-ai-glm-5-2:ce87a33d1a10c901",
      "capped_draws": 316,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 200,
      "draws": 316,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 167,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 490,
      "rating_method": "sequential_elo",
      "raw_elo": 1272.3808804357977,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.652257915135223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:xiaomi-mimo-v2-6-flash:2cbc2b572299d3d2",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1280.841049518355,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.29762262352045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:64e1b98629aed328",
      "capped_draws": 155,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 155,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T14:08:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1253.5592248137123,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.252817076331517,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-6-luna:d08f8d120a6f613c",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.9720176074093,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.12822117287516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-5-flash:099e26902a6430db",
      "capped_draws": 135,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 135,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 126,
      "max_score": null,
      "measured_at": "2026-09-22T10:58:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1201.1802064230644,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.312341613513716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:deepseek-deepseek-v4-1-flash:3af710709a8e8646",
      "capped_draws": 39,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1210.6336257419828,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.910316416776945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:z-ai-glm-5-3-flashx:02af860bd4bc6de7",
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1109.1345222853001,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.080049745365206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:nex-agi-nex-n2-pro:c0da63af5f63c563",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 198,
      "max_score": null,
      "measured_at": "2026-09-25T05:25:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1000.1996922567068,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1962,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-6-astra:24306100b4080f36",
      "capped_draws": 11,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.26443,
        "mean": 0.23918625000000002,
        "median": 0.241805,
        "min": 0.2072175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-05": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.9134900000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 76.98193882052338,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 285,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:30Z",
      "losses": 211,
      "max_score": 97.38715231698653,
      "measured_at": null,
      "min_score": 50.02617127882385,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1962,
      "rating_method": "sequential_elo",
      "raw_elo": 1961.253142422849,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 76.98193882052338,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1466
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1924,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-fable-5-1:82fc3985d63b4a72",
      "capped_draws": 2,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.8940315948861309,
        "mean": 0.7923815012907612,
        "median": 0.7948316688813246,
        "min": 0.6566066208996896,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 6.33905201032609
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 74.53643108789285,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 217,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:44:45Z",
      "losses": 217,
      "max_score": 88.63477864319661,
      "measured_at": null,
      "min_score": 54.829742723095954,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1918,
      "rating_method": "sequential_elo",
      "raw_elo": 1932.842927550027,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 74.53643108789285,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1484
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 820,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-5-5:d1839e51632cc557",
      "capped_draws": 7,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.124844,
        "mean": 0.11677924999999999,
        "median": 0.118817,
        "min": 0.094852,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 9
        },
        "run_count": 9,
        "token_priced_attempt_count": 9,
        "total": 1.052792
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 59.7581605831015,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 128,
      "eligibility_flag": true,
      "entry_count": 9,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 9,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:34:12Z",
      "losses": 156,
      "max_score": 79.85364697365718,
      "measured_at": null,
      "min_score": 34.34311959065729,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 820,
      "rating_method": "sequential_elo",
      "raw_elo": 1775.8111490247318,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 59.7581605831015,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 536
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 3124,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 224,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.5221625,
        "mean": 0.2856328125,
        "median": 0.2536225,
        "min": 0.2178175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 4.570125000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 59.77980290368503,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 630,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:04:48Z",
      "losses": 544,
      "max_score": 88.30380211671529,
      "measured_at": null,
      "min_score": 30.879083926934985,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3121,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.8890072464121,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 57.81712497651046,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1947
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2090,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-fable-5:7f6b2a08dddc3940",
      "capped_draws": 61,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.35085,
        "mean": 0.28860625,
        "median": 0.282885,
        "min": 0.22654,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 2.30885
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.59349239407559,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 527,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:59:44Z",
      "losses": 627,
      "max_score": 70.75317794233399,
      "measured_at": null,
      "min_score": 8.30135369548809,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2088,
      "rating_method": "sequential_elo",
      "raw_elo": 1642.0653756966155,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 46.59349239407559,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 934
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 720,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-6-sol:3e255a0c8d7168aa",
      "capped_draws": 6,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.052136,
        "mean": 0.043196000000000005,
        "median": 0.04354475,
        "min": 0.033231000000000004,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.345568
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.49429384120996,
      "contributing_entrants": null,
      "distinct_rated_opponents": 65,
      "draws": 133,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:24:43Z",
      "losses": 214,
      "max_score": 67.0440325823212,
      "measured_at": null,
      "min_score": 11.969256362592526,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 720,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.3676025098832,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 46.49429384120996,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 373
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3506,
      "canonical_public_row_identity": "publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 300,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.1077678,
        "mean": 0.076003275,
        "median": 0.070269,
        "min": 0.0550338,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.6080262
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.71441221564036,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 942,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:55:04Z",
      "losses": 1150,
      "max_score": 88.12366220504157,
      "measured_at": null,
      "min_score": 16.87963566446718,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 1.0,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3506,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.1727110036659,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 42.71441221564036,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1414
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3096,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 51,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.15394249999999998,
        "mean": 0.12786562499999998,
        "median": 0.13029000000000002,
        "min": 0.10071375,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.0229249999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.26651060228551,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 710,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:36:49Z",
      "losses": 1005,
      "max_score": 67.54145227969542,
      "measured_at": null,
      "min_score": 9.182072363962202,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3095,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.5380177712655,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 42.26651060228551,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1380
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2202,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-8-flash:bf006bcd6ccb81c6",
      "capped_draws": 176,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.041197616649628,
        "mean": 0.031941679879238995,
        "median": 0.03128326283110872,
        "min": 0.026892580852245062,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.25553343903391196
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.5414993237416,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 567,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:09:49Z",
      "losses": 743,
      "max_score": 68.57629933967782,
      "measured_at": null,
      "min_score": 7.419192145713985,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2201,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.735873075744,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 41.5414993237416,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 891
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2230,
      "canonical_public_row_identity": "publication-row.v1:baseline:z-ai-glm-5-3:d95da7acd9780380",
      "capped_draws": 208,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.1610404,
        "mean": 0.053977109999999995,
        "median": 0.0318207,
        "min": 0.0217974,
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.43181688
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.754746612238606,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 741,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:01Z",
      "losses": 767,
      "max_score": 67.95978288951696,
      "measured_at": null,
      "min_score": 15.003603712634062,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2227,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.9869711196268,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.754746612238606,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 719
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2184,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-8-2-4t-a95b:2caf8bc899f551f3",
      "capped_draws": 118,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.2163622471450082,
        "mean": 0.1497312219916341,
        "median": 0.14598267318350014,
        "min": 0.09347384547152984,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 1.1978497759330726
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.579637006781816,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 604,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:34:02Z",
      "losses": 770,
      "max_score": 60.087876316969584,
      "measured_at": null,
      "min_score": 19.63268358764324,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2183,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.7466459683415,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.579637006781816,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 809
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 600,
      "canonical_public_row_identity": "publication-row.v1:baseline:x-ai-grok-4-7:e9b5a4757d911202",
      "capped_draws": 27,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.143752,
        "mean": 0.082967,
        "median": 0.0730072,
        "min": 0.0533856,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 10
        },
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.663736
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.01861015130885,
      "contributing_entrants": null,
      "distinct_rated_opponents": 66,
      "draws": 118,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:34:01Z",
      "losses": 243,
      "max_score": 71.24448433375413,
      "measured_at": null,
      "min_score": 15.846953534414173,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": 0.875,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 600,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.082586073285,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 37.737559341951254,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 239
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3274,
      "canonical_public_row_identity": "publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 261,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.0992248,
        "mean": 0.07433795,
        "median": 0.0774068,
        "min": 0.0424244,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.5947036
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 37.08056429204913,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 969,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:51:32Z",
      "losses": 1152,
      "max_score": 67.15463779430945,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3274,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.2248047238807,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 37.08056429204913,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1153
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1730,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-4-5:024e2b4b1f467362",
      "capped_draws": 167,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.144235,
        "mean": 0.12174125,
        "median": 0.121475,
        "min": 0.09594,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.9739300000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.88094431118054,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 550,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:46Z",
      "losses": 583,
      "max_score": 65.59804006842714,
      "measured_at": null,
      "min_score": 13.849919257531704,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1730,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.4999610577722,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 36.88094431118054,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 597
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2116,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 240,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.173358,
        "mean": 0.1197105,
        "median": 0.119348,
        "min": 0.066054,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.957684
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.2882702960712,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 740,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:32Z",
      "losses": 691,
      "max_score": 90.1443955387162,
      "measured_at": null,
      "min_score": 12.573076409935867,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2116,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.850176044393,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 36.2882702960712,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 685
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 716,
      "canonical_public_row_identity": "publication-row.v1:baseline:z-ai-glm-5-3-flashx:1240fd0f864b9059",
      "capped_draws": 58,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.01270098,
        "mean": 0.0085203375,
        "median": 0.007669445,
        "min": 0.00543595,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 10
        },
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.0681627
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.528031155574,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 203,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:54Z",
      "losses": 288,
      "max_score": 57.68992736691443,
      "measured_at": null,
      "min_score": 7.915683771374111,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 716,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.0846377672417,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.528031155574,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 225
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2786,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 290,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.179715,
        "mean": 0.09608781250000001,
        "median": 0.08063500000000001,
        "min": 0.0656625,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.7687025000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.34236797788512,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 916,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:03:32Z",
      "losses": 1020,
      "max_score": 63.18239982783971,
      "measured_at": null,
      "min_score": 9.220151455961185,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2786,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.9157630074324,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.34236797788512,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 850
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2148,
      "canonical_public_row_identity": "publication-row.v1:baseline:z-ai-glm-5-3-flash:1c774d2a8faa3025",
      "capped_draws": 310,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.0140393,
        "mean": 0.0037309874999999996,
        "median": 0.0024275875,
        "min": 0.001111625,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.0298479
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.18744561545431,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 704,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:53:18Z",
      "losses": 805,
      "max_score": 63.151925655306094,
      "measured_at": null,
      "min_score": 11.498805673082217,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2148,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.6459344257833,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.18744561545431,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 639
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2160,
      "canonical_public_row_identity": "publication-row.v1:baseline:tencent-hy4-preview:9b637fbe1929d4b6",
      "capped_draws": 243,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.028804516000000002,
        "mean": 0.015939765625,
        "median": 0.0150484685,
        "min": 0.009391185,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.127518125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.083880829330376,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 727,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:00Z",
      "losses": 794,
      "max_score": 51.36592552964594,
      "measured_at": null,
      "min_score": 11.032703602266714,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": 1.0,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2160,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.1192351310904,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.083880829330376,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 639
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 636,
      "canonical_public_row_identity": "publication-row.v1:baseline:xiaomi-mimo-v2-6-flash:462b03a9e092439a",
      "capped_draws": 72,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00414456,
        "mean": 0.0029296749999999996,
        "median": 0.00284053,
        "min": 0.00188342,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 12
        },
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.0234374
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.62005544829645,
      "contributing_entrants": null,
      "distinct_rated_opponents": 68,
      "draws": 174,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:55Z",
      "losses": 292,
      "max_score": 54.30649302297495,
      "measured_at": null,
      "min_score": 11.524793275000588,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": 0.875,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.2241957357637,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.45058527279682,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1520,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-4-8:ff1cf2191e10c995",
      "capped_draws": 43,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.190125,
        "mean": 0.15785312499999998,
        "median": 0.15388000000000002,
        "min": 0.131495,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.2628249999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.51231631187023,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 410,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:28:44Z",
      "losses": 532,
      "max_score": 65.98085473100755,
      "measured_at": null,
      "min_score": 9.918422916272286,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1520,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.067255671283,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.34638340505811,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 578
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 670,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-8-max-0902:565f7de155dcf265",
      "capped_draws": 92,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.212408,
        "mean": 0.12122175,
        "median": 0.11379500000000001,
        "min": 0.08249,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 10
        },
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.969774
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.088585523137525,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 228,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:17:39Z",
      "losses": 234,
      "max_score": 71.7714779302936,
      "measured_at": null,
      "min_score": 2.3421974844057343,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 670,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.385584713357,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.088585523137525,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 208
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 726,
      "canonical_public_row_identity": "publication-row.v1:baseline:xiaomi-mimo-v2-6-pro:a01ac332611439f7",
      "capped_draws": 33,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.01198425,
        "mean": 0.00718913625,
        "median": 0.0061211025,
        "min": 0.005105595,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 10
        },
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.057513089999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.96387114069511,
      "contributing_entrants": null,
      "distinct_rated_opponents": 69,
      "draws": 168,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:21:57Z",
      "losses": 330,
      "max_score": 57.09922504114827,
      "measured_at": null,
      "min_score": 3.415118568191135,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": 1.0,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 726,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.416019408977,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.96387114069511,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 228
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": 7770,
      "canonical_public_row_identity": "publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 754,
      "codegen_cost_usd": {
        "admitted_cell_count": 28,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 42
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 42,
        "run_count": 30,
        "total": 0.0
      },
      "codegen_evaluated_cells": 30,
      "conditional_success_score": 33.934700850619244,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2779,
      "eligibility_flag": true,
      "entry_count": 28,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 19,
      "first_pass_rate": 0.6333333333333333,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:01Z",
      "losses": 2845,
      "max_score": 51.393316198139864,
      "measured_at": null,
      "min_score": 13.796926219903233,
      "model_code_failure_rate": 0.06666666666666667,
      "model_code_failures": 2,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": 0.9333333333333333,
      "provider": "Other",
      "provider_key": "other",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 7756,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.6304550290656,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 9,
      "repaired_rate": 0.3,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 33.354406643828256,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 2132
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1500,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-7-max:79acf3b5f6851440",
      "capped_draws": 225,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.03912625,
        "mean": 0.022799843750000003,
        "median": 0.021642500000000002,
        "min": 0.015285,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.18239875
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.87093314013739,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 472,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:54:10Z",
      "losses": 588,
      "max_score": 59.48821171455273,
      "measured_at": null,
      "min_score": 15.277846845543255,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": 0.875,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1500,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.7731674081672,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 32.75888978070947,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 440
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2346,
      "canonical_public_row_identity": "publication-row.v1:baseline:x-ai-grok-4-6:f1d4c61e0708aeae",
      "capped_draws": 248,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.041774,
        "mean": 0.03185375,
        "median": 0.031432,
        "min": 0.027072,
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.25483
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.46340977658835,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 859,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:19:40Z",
      "losses": 869,
      "max_score": 50.80866287227604,
      "measured_at": null,
      "min_score": 12.14033355812917,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2346,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.509435957214,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 32.46340977658835,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 618
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2914,
      "canonical_public_row_identity": "publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 152,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.03564825,
        "mean": 0.0239263125,
        "median": 0.02294625,
        "min": 0.01939525,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.1914105
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.31949261917336,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 696,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:14:24Z",
      "losses": 1295,
      "max_score": 56.41476958488925,
      "measured_at": null,
      "min_score": 8.986553392204476,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2914,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.1490833417463,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 32.31949261917336,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 923
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 6603,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 782,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.07826175,
        "mean": 0.05584070625,
        "median": 0.0541695,
        "min": 0.0411735,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 0.8934513000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 31.86715852062013,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 2263,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 12,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:10:53Z",
      "losses": 2594,
      "max_score": 51.905912358610884,
      "measured_at": null,
      "min_score": 11.07482345464506,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6597,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.316512538555,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 31.86715852062013,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1740
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2984,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 243,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.07847,
        "mean": 0.06167125,
        "median": 0.061313,
        "min": 0.051588,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.49337
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.62514039383202,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 886,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:44:45Z",
      "losses": 1217,
      "max_score": 42.31219893783358,
      "measured_at": null,
      "min_score": 13.478477269301598,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2984,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.0844308593921,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 31.62514039383202,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 881
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2170,
      "canonical_public_row_identity": "publication-row.v1:baseline:meta-muse-spark-1-3:b665bb24258fc911",
      "capped_draws": 275,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.043892749999999994,
        "mean": 0.023888718750000003,
        "median": 0.020423875,
        "min": 0.017614,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.19110975000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.068787453123537,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 712,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:55Z",
      "losses": 830,
      "max_score": 47.149913347085835,
      "measured_at": null,
      "min_score": 13.707425405221867,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2162,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.101072914798,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 31.068787453123537,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 620
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1808,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-4-1:e60d2fa1e7162f32",
      "capped_draws": 188,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.09459400000000001,
        "mean": 0.0571955,
        "median": 0.043012,
        "min": 0.032534,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 0.457564
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.876939936900786,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 620,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:04:41Z",
      "losses": 670,
      "max_score": 53.67468803008354,
      "measured_at": null,
      "min_score": 6.9862813021302,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1807,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.471458583072,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.876939936900786,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 517
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 6376,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 790,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.0222516,
        "mean": 0.01697319375,
        "median": 0.015739925000000002,
        "min": 0.012759,
        "recorded_attempt_count": 34,
        "run_count": 16,
        "total": 0.2715711
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 30.82157899867084,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1981,
      "eligibility_flag": true,
      "entry_count": 15,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:00Z",
      "losses": 2605,
      "max_score": 56.66854839969095,
      "measured_at": null,
      "min_score": 8.198390781857146,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.9375,
      "provider": "Google",
      "provider_key": "google",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6369,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.6901992754015,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.32827456073786,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1783
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 5184,
      "canonical_public_row_identity": "publication-row.v1:baseline:z-ai-glm-5-2:51bd53334ebd6ddf",
      "capped_draws": 518,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.03729904666666666,
        "mean": 0.023546225995833333,
        "median": 0.024102434966666666,
        "min": 0.013816857666666668,
        "recorded_attempt_count": 37,
        "run_count": 24,
        "total": 0.5651094239
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 30.29805723378784,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1748,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:34:04Z",
      "losses": 1966,
      "max_score": 46.703813687928275,
      "measured_at": null,
      "min_score": 8.254948532527202,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5184,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.0187214468885,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.29805723378784,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1470
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 3011,
      "canonical_public_row_identity": "publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 485,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.00407402,
        "mean": 0.0029986699999999997,
        "median": 0.00314426,
        "min": 0.0012446800000000002,
        "recorded_attempt_count": 33,
        "run_count": 14,
        "total": 0.04176386
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 31.432327599551694,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 935,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:09:29Z",
      "losses": 1207,
      "max_score": 46.950499952815655,
      "measured_at": null,
      "min_score": 10.592781159581312,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 2,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": 0.8571428571428571,
      "provider": "Other",
      "provider_key": "other",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3002,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.4596568833645,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 5,
      "repaired_rate": 0.35714285714285715,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.244042856809923,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 860
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1540,
      "canonical_public_row_identity": "publication-row.v1:baseline:deepseek-deepseek-v4-pro-0813:62f039a975dbbc18",
      "capped_draws": 275,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0508167,
        "mean": 0.02704530848,
        "median": 0.020221080000000002,
        "min": 0.01808105112,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.21636246784
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.779004608881248,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 584,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-05"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:19:40Z",
      "losses": 630,
      "max_score": 57.44640162344343,
      "measured_at": null,
      "min_score": 18.481794861921347,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": 0.75,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1534,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.5828214183366,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 29.573696106452907,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 320
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1470,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-5:62529dcffe2e7fae",
      "capped_draws": 335,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.156555,
        "mean": 0.1422525,
        "median": 0.14850249999999998,
        "min": 0.12078,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.13802
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 29.975112307677914,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 724,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:10:59Z",
      "losses": 443,
      "max_score": 49.045069424600065,
      "measured_at": null,
      "min_score": 12.771607546272488,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1469,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.2829276169302,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 28.990975719177527,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 302
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1356,
      "canonical_public_row_identity": "publication-row.v1:baseline:minimax-minimax-m3:187f6e5e3d0ad827",
      "capped_draws": 60,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.09803328,
        "mean": 0.0253809975,
        "median": 0.00943521,
        "min": 0.00639384,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.20304798000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.376605494931567,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 306,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:53:18Z",
      "losses": 601,
      "max_score": 42.47095379427678,
      "measured_at": null,
      "min_score": 8.021854667018928,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": 0.75,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1356,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.0152405891342,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 28.268616676610854,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 449
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 2000,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-terra:9663b021bc677328",
      "capped_draws": 305,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.136415,
        "mean": 0.07671781250000001,
        "median": 0.0705246875,
        "min": 0.058876874999999995,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.6137425000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 29.121872292278997,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 820,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-05"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:25:05Z",
      "losses": 725,
      "max_score": 47.475109428289485,
      "measured_at": null,
      "min_score": 12.122561741654145,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2000,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.4835273318854,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 28.16574910066959,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 455
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1582,
      "canonical_public_row_identity": "publication-row.v1:baseline:deepseek-deepseek-v4-pro:ff3e59d607a4ac18",
      "capped_draws": 282,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.03845835,
        "mean": 0.025296556802625002,
        "median": 0.02540433020275,
        "min": 0.014466934,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.20237245442100005
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 29.985795436779895,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 567,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-06"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:42Z",
      "losses": 563,
      "max_score": 44.02962894499428,
      "measured_at": null,
      "min_score": 14.507335399739189,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": 0.75,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1576,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.880059482926,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 27.904926937508936,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 446
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1510,
      "canonical_public_row_identity": "publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:577995919d91fce3",
      "capped_draws": 215,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.1311545862,
        "mean": 0.0317000854,
        "median": 0.0104556789,
        "min": 0.0057139812,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.2536006832
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.551607363877064,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 472,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:23:52Z",
      "losses": 621,
      "max_score": 47.29932137115699,
      "measured_at": null,
      "min_score": 4.615901320625215,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": 0.875,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1510,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.7441725839033,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 27.614206990564995,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 417
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1900,
      "canonical_public_row_identity": "publication-row.v1:baseline:deepseek-deepseek-v4-flash:b05f493f9c8d196b",
      "capped_draws": 197,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00200925116,
        "mean": 0.0013339496149999998,
        "median": 0.0012586017,
        "min": 0.0008945895,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 0.01067159692
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.2443395218878,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 548,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:18Z",
      "losses": 865,
      "max_score": 56.07127974669768,
      "measured_at": null,
      "min_score": 11.032375086013085,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.875,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1900,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.290362745103,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 27.31702730179655,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 487
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2184,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-8-flash:2ed602cefebb326c",
      "capped_draws": 291,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.006158996,
        "mean": 0.00343607875,
        "median": 0.002791493,
        "min": 0.0021123,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.02748863
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.59584737354384,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 793,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:23Z",
      "losses": 952,
      "max_score": 56.77974293719396,
      "measured_at": null,
      "min_score": 8.785005477286392,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2184,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.6126849228663,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.59584737354384,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 439
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1342,
      "canonical_public_row_identity": "publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:88820f6e6feb1287",
      "capped_draws": 208,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.13485595000000003,
        "mean": 0.031792056250000006,
        "median": 0.0158481,
        "min": 0.0111232,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 0.38919240000000005
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 28.154386641135257,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 438,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-07"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.5555555555555556,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:33Z",
      "losses": 614,
      "max_score": 51.8801788071995,
      "measured_at": null,
      "min_score": 4.923730589416949,
      "model_code_failure_rate": 0.2222222222222222,
      "model_code_failures": 2,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": 0.7777777777777778,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1342,
      "rating_method": "sequential_elo",
      "raw_elo": 1309.2659363491496,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.43990881752858,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 290
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 2564,
      "canonical_public_row_identity": "publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 181,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0721503,
        "mean": 0.03677837187500001,
        "median": 0.0324098875,
        "min": 0.01945095,
        "recorded_attempt_count": 39,
        "run_count": 16,
        "total": 0.58845395
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 28.224103029781716,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 768,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.4375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:34:28Z",
      "losses": 1140,
      "max_score": 59.97193472120926,
      "measured_at": null,
      "min_score": 9.390653049669545,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2562,
      "rating_method": "sequential_elo",
      "raw_elo": 1358.6958136472904,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.265487423313154,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 654
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 2532,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4-nano:44bc85871c51c275",
      "capped_draws": 291,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 27
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.01311555,
        "mean": 0.009215359375,
        "median": 0.009537575,
        "min": 0.004854125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 27
        },
        "run_count": 16,
        "token_priced_attempt_count": 27,
        "total": 0.14744575000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.883782722007982,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 726,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-07"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:12Z",
      "losses": 1137,
      "max_score": 42.52477509866081,
      "measured_at": null,
      "min_score": 10.4996181061563,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2532,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.7801891533904,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.948783691247797,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 669
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 3184,
      "canonical_public_row_identity": "publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 569,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 38
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.021206376000000002,
        "mean": 0.01337795025,
        "median": 0.01381146,
        "min": 0.006392298,
        "recorded_attempt_count": 38,
        "run_count": 16,
        "total": 0.214047204
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 26.51917609731877,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 1040,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:09Z",
      "losses": 1368,
      "max_score": 41.60041525625513,
      "measured_at": null,
      "min_score": 7.685379769827811,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": 0.875,
      "provider": "Other",
      "provider_key": "other",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3179,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.9607934211472,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.648504080267767,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 771
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 696,
      "canonical_public_row_identity": "publication-row.v1:baseline:deepseek-deepseek-v4-1-flash:4de18974b2d2aef7",
      "capped_draws": 93,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.007391933999999999,
        "mean": 0.00359850675,
        "median": 0.003217359,
        "min": 0.00220635,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.028788053999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 24.77717097795133,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 248,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:23Z",
      "losses": 327,
      "max_score": 39.43678310527615,
      "measured_at": null,
      "min_score": 11.271801424400126,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 696,
      "rating_method": "sequential_elo",
      "raw_elo": 1333.3426808937743,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 24.77717097795133,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 121
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1540,
      "canonical_public_row_identity": "publication-row.v1:baseline:openai-gpt-oss-120b:e4864d083f4798c2",
      "capped_draws": 245,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.002555,
        "mean": 0.001231986375,
        "median": 0.0010393855,
        "min": 0.00046744,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.009855891
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.57466175163876,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 531,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:44:38Z",
      "losses": 687,
      "max_score": 45.228110399238034,
      "measured_at": null,
      "min_score": 9.845665543687444,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1540,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.6146599066324,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 24.730509355069742,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 322
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 3466,
      "canonical_public_row_identity": "publication-row.v1:baseline:xiaomi-mimo-v2-5:8edac6f11a62a0aa",
      "capped_draws": 420,
      "codegen_cost_usd": {
        "admitted_cell_count": 17,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.005169185000000001,
        "mean": 0.002871050658333333,
        "median": 0.0023354879666666667,
        "min": 0.00169122,
        "recorded_attempt_count": 37,
        "run_count": 24,
        "total": 0.0689052158
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 25.848879605846548,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 961,
      "eligibility_flag": true,
      "entry_count": 17,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.4375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:04:48Z",
      "losses": 1625,
      "max_score": 35.70563172240146,
      "measured_at": null,
      "min_score": 6.460914561290655,
      "model_code_failure_rate": 0.3125,
      "model_code_failures": 5,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.6875,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3464,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.02080103489,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.537476498710557,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 878
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1798,
      "canonical_public_row_identity": "publication-row.v1:baseline:bytedance-seed-seed-2-0-code:95b26b11b0986534",
      "capped_draws": 274,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.030187,
        "mean": 0.020951124999999998,
        "median": 0.0183875,
        "min": 0.0121355,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.16760900000000004
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 24.18388960192967,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 538,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:52:14Z",
      "losses": 905,
      "max_score": 31.350179723882725,
      "measured_at": null,
      "min_score": 15.908866749062488,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": 0.875,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1792,
      "rating_method": "sequential_elo",
      "raw_elo": 1250.312007575009,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.389889220372577,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 349
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1360,
      "canonical_public_row_identity": "publication-row.v1:baseline:tencent-hy3-preview:6e31f3e29e62eb16",
      "capped_draws": 237,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.001632522,
        "mean": 0.00126739675,
        "median": 0.001232095,
        "min": 0.00090937,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.010139173999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 25.065186174186948,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 598,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:27:20Z",
      "losses": 460,
      "max_score": 57.73838761870533,
      "measured_at": null,
      "min_score": 3.2968970313112287,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": 0.75,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1360,
      "rating_method": "sequential_elo",
      "raw_elo": 1381.4403929843977,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.32578404799714,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 302
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1362,
      "canonical_public_row_identity": "publication-row.v1:baseline:inception-mercury-2-5-preview:ae4030f1f9433705",
      "capped_draws": 16,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0013895600000000002,
        "mean": 0.0009515637499999999,
        "median": 0.001025285,
        "min": 0.00044038,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.007612509999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.056088009018758,
      "contributing_entrants": null,
      "distinct_rated_opponents": 69,
      "draws": 549,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:09:48Z",
      "losses": 516,
      "max_score": 38.37213841472128,
      "measured_at": null,
      "min_score": 14.830792683984784,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": 0.625,
      "provider": "Other",
      "provider_key": "other",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1361,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.6315089367552,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.167502406300063,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 296
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2103,
      "canonical_public_row_identity": "publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 277,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.014791950000000002,
        "mean": 0.007616140625,
        "median": 0.005694875,
        "min": 0.00430875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 0.07206399999999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 23.22904400122249,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 841,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.5555555555555556,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:05:49Z",
      "losses": 925,
      "max_score": 35.60527077189641,
      "measured_at": null,
      "min_score": 6.993147556840411,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "Other",
      "provider_key": "other",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2096,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.2898984859337,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 22.555019454441762,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 330
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1658,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4-mini:35d10d5994080add",
      "capped_draws": 246,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.03021,
        "mean": 0.0183815625,
        "median": 0.015581250000000001,
        "min": 0.01245825,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.1470525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 21.94285654112259,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 730,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:36:58Z",
      "losses": 701,
      "max_score": 35.293552338742806,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1654,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.3642085222577,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 21.94285654112259,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 223
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1570,
      "canonical_public_row_identity": "publication-row.v1:baseline:meta-muse-glimmer-30b:5f799292ad06c854",
      "capped_draws": 275,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.01024177,
        "mean": 0.0073127075,
        "median": 0.007628165,
        "min": 0.00402612,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.05850166
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 23.31994578837838,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 573,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-06"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:41:55Z",
      "losses": 705,
      "max_score": 34.62208396746334,
      "measured_at": null,
      "min_score": 6.328311136424571,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1570,
      "rating_method": "sequential_elo",
      "raw_elo": 1264.894672818974,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 21.701654864662462,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 292
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2566,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 151,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.0057713,
        "mean": 0.004598475,
        "median": 0.0045067,
        "min": 0.0040101,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.0367878
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 19.663828504380618,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 818,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:54Z",
      "losses": 1417,
      "max_score": 32.88038109999295,
      "measured_at": null,
      "min_score": 8.701180641503443,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2566,
      "rating_method": "sequential_elo",
      "raw_elo": 1242.382645008762,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 19.663828504380618,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 331
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1304,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-7-plus:a3ea745ea8da84ce",
      "capped_draws": 47,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0154064,
        "mean": 0.00874386,
        "median": 0.0064215999999999995,
        "min": 0.00524064,
        "recorded_attempt_count": 13,
        "run_count": 9,
        "total": 0.08145696000000001
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 20.17038574595111,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 436,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.4444444444444444,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:11:47Z",
      "losses": 644,
      "max_score": 43.55040400948236,
      "measured_at": null,
      "min_score": 9.261021826492382,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 3,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": 0.6666666666666666,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1301,
      "rating_method": "sequential_elo",
      "raw_elo": 1234.2952432543084,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 18.226000973624874,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 221
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1678,
      "canonical_public_row_identity": "publication-row.v1:baseline:mistralai-mistral-medium-3-5:283b3ca34d89e95f",
      "capped_draws": 223,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 12
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.11538050836051075,
        "mean": 0.06762316700208985,
        "median": 0.06087263456058671,
        "min": 0.04290565490575157,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 12
        },
        "run_count": 8,
        "token_priced_attempt_count": 12,
        "total": 0.5409853360167187
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 18.520382849552355,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 611,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-07"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:34:04Z",
      "losses": 862,
      "max_score": 32.358999465512234,
      "measured_at": null,
      "min_score": 3.83400018350949,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": 0.875,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1677,
      "rating_method": "sequential_elo",
      "raw_elo": 1247.6934407492552,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 17.91232553159492,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 204
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 2508,
      "canonical_public_row_identity": "publication-row.v1:baseline:inclusionai-ling-3-0-flash:003df1488166fe5c",
      "capped_draws": 580,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 40
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 40,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 18.550407116525978,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 1161,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-07"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:10:59Z",
      "losses": 1021,
      "max_score": 35.962389688777634,
      "measured_at": null,
      "min_score": 11.38300416268924,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 6,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": 0.625,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2506,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.4602134177467,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 16.493903511578825,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 324
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 980,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-1-flash-lite:38c057fa340718ef",
      "capped_draws": 46,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.00870475,
        "mean": 0.005883593750000001,
        "median": 0.006313125,
        "min": 0.003432,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.04706874999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 14.858192619973412,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 233,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:26:38Z",
      "losses": 606,
      "max_score": 32.38410669171022,
      "measured_at": null,
      "min_score": 0.08310002118024254,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": 0.625,
      "provider": "Google",
      "provider_key": "google",
      "rank": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 980,
      "rating_method": "sequential_elo",
      "raw_elo": 1103.9846183775826,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 13.211009003245497,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 400,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-4-1-nano:e6370d2aaad0f23a",
      "capped_draws": 73,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 1,
        "cost_basis_counts": {
          "estimated": 1,
          "local_standard_estimate": 1
        },
        "cost_is_complete": false,
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "max": 0.0023425,
        "mean": 0.0023425,
        "median": 0.0023425,
        "min": 0.0023425,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 1,
          "boardgame-list-prices-2026-09-08": 1
        },
        "recorded_attempt_count": 1,
        "run_count": 1,
        "token_priced_attempt_count": 1,
        "total": 0.0023425
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": 42.384495360660594,
      "contributing_entrants": null,
      "distinct_rated_opponents": 55,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": 1,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1-nano",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 1,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T04:52:57Z",
      "losses": 167,
      "max_score": 42.384495360660594,
      "measured_at": null,
      "min_score": 42.384495360660594,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 400,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.7109953757326,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Reasoning field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 42.384495360660594,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5:3f22d9cfc88a4f65",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 12
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.15380375000000002,
        "mean": 0.09741312500000002,
        "median": 0.090410625,
        "min": 0.06945125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 12
        },
        "run_count": 8,
        "token_priced_attempt_count": 12,
        "total": 0.7793050000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.56397705047057,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 281,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:55:04Z",
      "losses": 327,
      "max_score": 58.418681017299306,
      "measured_at": null,
      "min_score": 3.1304801359516308,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 836,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.0643293859027,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 29.373590415755068,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 228
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1712,
      "canonical_public_row_identity": "publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 284,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.03772852,
        "mean": 0.024905897500000003,
        "median": 0.026095300000000002,
        "min": 0.00984735,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.19924718
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 33.99334325098176,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 316,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:41:47Z",
      "losses": 878,
      "max_score": 43.52073030334479,
      "measured_at": null,
      "min_score": 21.499809680072865,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": 0.5,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1708,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.7086739050835,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 28.584880482239612,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 514
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-5-flash:8f1504913d7602c4",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11,
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Combined: Provider-reported + Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.12650943660072694,
        "mean": 0.07695988119919009,
        "median": 0.07334251535992004,
        "min": 0.043710665151447045,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "recorded_attempt_count": 14,
        "run_count": 16,
        "token_priced_attempt_count": 11,
        "total": 1.2313580991870414
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 25.885929283914564,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 932,
      "eligibility_flag": false,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:59:45Z",
      "losses": 1242,
      "max_score": 45.182063451624146,
      "measured_at": null,
      "min_score": 5.490992930648422,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 2894,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.4294455370973,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.885929283914564,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 720
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 636,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-6-luna:ec8acee7f417cae7",
      "capped_draws": 73,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 7,
        "cost_basis_counts": {
          "local_standard_estimate": 7
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.0030818,
        "mean": 0.0023309607142857143,
        "median": 0.0023213,
        "min": 0.00161355,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 7
        },
        "run_count": 7,
        "token_priced_attempt_count": 7,
        "total": 0.016316724999999997
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 25.376707397121997,
      "contributing_entrants": null,
      "distinct_rated_opponents": 65,
      "draws": 216,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-07"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:25:00Z",
      "losses": 319,
      "max_score": 47.74933846094135,
      "measured_at": null,
      "min_score": 10.200783051786512,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.7360625953631,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.376707397121997,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1622,
      "canonical_public_row_identity": "publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 392,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 8,
          "local_standard_estimate": 13
        },
        "cost_is_complete": false,
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.17217,
        "mean": 0.11039474999999999,
        "median": 0.10846,
        "min": 0.07562,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 13,
          "boardgame-list-prices-2026-09-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "token_priced_attempt_count": 13,
        "total": 0.8831579999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.37225226289518,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 445,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:14:18Z",
      "losses": 878,
      "max_score": 37.04284479501129,
      "measured_at": null,
      "min_score": 15.926557852896163,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.5,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1622,
      "rating_method": "sequential_elo",
      "raw_elo": 1220.829991234879,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 22.176332390035217,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 299
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1372,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemma-4-31b-it:b471a27d319d0e3f",
      "capped_draws": 225,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00391754,
        "mean": 0.0023617857142857143,
        "median": 0.00186618,
        "min": 0.00144036,
        "recorded_attempt_count": 8,
        "run_count": 7,
        "total": 0.0165325
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 22.312855735333248,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 389,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.7142857142857143,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:10:59Z",
      "losses": 685,
      "max_score": 40.745990007722504,
      "measured_at": null,
      "min_score": 12.918261292629804,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 1,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": 0.8571428571428571,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1370,
      "rating_method": "sequential_elo",
      "raw_elo": 1211.2628902479948,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.14285714285714285,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 21.469328447914897,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 296
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1542,
      "canonical_public_row_identity": "publication-row.v1:baseline:nex-agi-nex-n2-pro:b38db13dbc86bdcd",
      "capped_draws": 207,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 36
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.215758025,
        "mean": 0.16162675,
        "median": 0.1594081875,
        "min": 0.098579625,
        "recorded_attempt_count": 36,
        "run_count": 16,
        "total": 2.5860279999999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 25.922021453852462,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 661,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:24:54Z",
      "losses": 550,
      "max_score": 64.55194498926986,
      "measured_at": null,
      "min_score": 0.10631171802151808,
      "model_code_failure_rate": 0.5625,
      "model_code_failures": 9,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": 0.4375,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1542,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.8685609279673,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 21.082076264331786,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 331
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 658,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-8-27b:4712c07305d96aee",
      "capped_draws": 221,
      "codegen_cost_usd": {
        "admitted_cell_count": 3,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.045896320000000004,
        "mean": 0.021958409999999998,
        "median": 0.019045885,
        "min": 0.011539076,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.17566728000000004
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 25.815872048344037,
      "contributing_entrants": null,
      "distinct_rated_opponents": 62,
      "draws": 396,
      "eligibility_flag": false,
      "entry_count": 2,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-05",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold",
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T06:12:20Z",
      "losses": 149,
      "max_score": 26.00270887896228,
      "measured_at": null,
      "min_score": 25.6290352177258,
      "model_code_failure_rate": 0.625,
      "model_code_failures": 5,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": 0.375,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 634,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.1732387178658,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 20.202011632004123,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 24,
      "wins": 89
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1196,
      "canonical_public_row_identity": "publication-row.v1:baseline:cohere-north-mini-code:292c9223f5fe9dd2",
      "capped_draws": 350,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 30
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 30,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 21.057347774738698,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 350,
      "eligibility_flag": false,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.1875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:26:38Z",
      "losses": 674,
      "max_score": 23.265561771241,
      "measured_at": null,
      "min_score": 18.67245084542328,
      "model_code_failure_rate": 0.6875,
      "model_code_failures": 11,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": 0.3125,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1192,
      "rating_method": "sequential_elo",
      "raw_elo": 1190.145486192457,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": 2,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 15.744039665353446,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 168
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-6-astra:24306100b4080f36",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T04:05:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 2100.9518948550194,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 87.05513481232872,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 226
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-fable-5-1:82fc3985d63b4a72",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1957.9127540154252,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.72420952317101,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-5-5:d1839e51632cc557",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-09-25T12:45:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1919.7275498220986,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.71748095253615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-09-25T14:36:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.0464318648021,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.34042900452175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 235
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 390,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 170,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 153,
      "draws": 170,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T16:04:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 389,
      "rating_method": "sequential_elo",
      "raw_elo": 1758.9180116522066,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.28494267530827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 186
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 324,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1735.867496603253,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.092745140918936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 237
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-fable-5:7f6b2a08dddc3940",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1739.0114851123444,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.0616104086017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 124
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-7-max:79acf3b5f6851440",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T07:41:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1720.3951004144337,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.48821171455273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5:3f22d9cfc88a4f65",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T05:49:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1714.0103524224082,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.418681017299306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": null,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:tencent-hy3-preview:6e31f3e29e62eb16",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1695.1065782809987,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.73838761870533,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 132
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:xiaomi-mimo-v2-6-flash:462b03a9e092439a",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T12:05:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1664.6087584065551,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.30649302297495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-4-1:e60d2fa1e7162f32",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T16:04:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 199,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.496353573131,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.67468803008354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:z-ai-glm-5-3:d95da7acd9780380",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.22022848766,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.45667718141312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 284,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:x-ai-grok-4-6:f1d4c61e0708aeae",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T14:36:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1593.9305849143425,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.80866287227604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 155
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 483,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 261,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 156,
      "draws": 261,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-25T06:04:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 483,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.0089674152905,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.48880202945978,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-8-flash:bf006bcd6ccb81c6",
      "capped_draws": 139,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 139,
      "draws": 139,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-09-23T17:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.2037897524815,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.40200930687758,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-terra:9663b021bc677328",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 92,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.719470534291,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.475109428289485,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:88820f6e6feb1287",
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-09-25T06:46:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.923786506695,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.23098571326132,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:openai-gpt-oss-120b:e4864d083f4798c2",
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 48,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 156,
      "max_score": null,
      "measured_at": "2026-09-25T04:58:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.518874276408,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.228110399238034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-5-flash:8f1504913d7602c4",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 101,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 120,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.237961349977,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.182063451624146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.2375081760512119,
      "unilateral_faults": null,
      "wins": 155
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:z-ai-glm-5-3-flashx:1240fd0f864b9059",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T04:04:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.3827439630202,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.65314846921031,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-6-sol:3e255a0c8d7168aa",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.3851920559573,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.366545476309426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 452,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 170,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 185,
      "max_score": null,
      "measured_at": "2026-09-25T03:01:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 452,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.1664104314107,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.374154056993305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 174
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-4-8:ff1cf2191e10c995",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T12:45:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.5850112178202,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.54797429381968,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 400,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-4-1-nano:e6370d2aaad0f23a",
      "capped_draws": 73,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1-nano",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 167,
      "max_score": null,
      "measured_at": "2026-09-25T04:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 400,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.7109953757326,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Reasoning field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.384495360660594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 362,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4-nano:44bc85871c51c275",
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 150,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 139,
      "max_score": null,
      "measured_at": "2026-09-25T14:16:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 362,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.3205319946537,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.94845904405925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemma-4-31b-it:b471a27d319d0e3f",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.5486662112273,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.745990007722504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 880,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 228,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 373,
      "draws": 228,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 338,
      "max_score": null,
      "measured_at": "2026-09-25T15:07:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 880,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.3073110852486,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.52253717539108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 314
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 310,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:tencent-hy4-preview:9b637fbe1929d4b6",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 157,
      "max_score": null,
      "measured_at": "2026-09-25T14:36:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 310,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.673031897578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.82178269174233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 107
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:deepseek-deepseek-v4-1-flash:4de18974b2d2aef7",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.2053512148998,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.43678310527615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:minimax-minimax-m3:187f6e5e3d0ad827",
      "capped_draws": 43,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-09-25T15:53:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.9041066181655,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.62063436503806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-5:62529dcffe2e7fae",
      "capped_draws": 155,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 155,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T13:39:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.3813504804746,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.358374606065006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-4-5:024e2b4b1f467362",
      "capped_draws": 128,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 128,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T14:02:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.911565716598,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.19944229004737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 478,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 157,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 178,
      "draws": 157,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 177,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 478,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.5992831781336,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.44066886204282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 144
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 503,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 294,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 157,
      "draws": 294,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 117,
      "max_score": null,
      "measured_at": "2026-09-25T13:07:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 503,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.0231047535278,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.39954930655572,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:577995919d91fce3",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-09-25T12:55:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.2533977452536,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.36361428580678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 141,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 141,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-25T13:39:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.9136376508068,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.24566499417282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 400,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 139,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 199,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 400,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.965015024976,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.882220925455094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 139
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:xiaomi-mimo-v2-6-pro:a01ac332611439f7",
      "capped_draws": 33,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T04:10:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.4912292460306,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.02595884308104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 500,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:inclusionai-ling-3-0-flash:003df1488166fe5c",
      "capped_draws": 141,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 174,
      "draws": 141,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 214,
      "max_score": null,
      "measured_at": "2026-09-25T14:36:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 500,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.4078953975363,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.962389688777634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 866,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 168,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 278,
      "draws": 168,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 428,
      "max_score": null,
      "measured_at": "2026-09-25T14:16:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 866,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.2001559215114,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.948564706388524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 270
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4-mini:35d10d5994080add",
      "capped_draws": 75,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.239729616377,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.293552338742806,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:meta-muse-glimmer-30b:5f799292ad06c854",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-09-25T04:00:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.763742153872,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.62208396746334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:z-ai-glm-5-3-flash:1c774d2a8faa3025",
      "capped_draws": 153,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 125,
      "draws": 153,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-09-25T15:53:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.3289139357905,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.24431379862208,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 574,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:xiaomi-mimo-v2-5:8edac6f11a62a0aa",
      "capped_draws": 109,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 227,
      "draws": 109,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 273,
      "max_score": null,
      "measured_at": "2026-09-25T16:04:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 574,
      "rating_method": "sequential_elo",
      "raw_elo": 1366.5223723078952,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.15919658613578,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 192
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:deepseek-deepseek-v4-pro-0813:62f039a975dbbc18",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T13:19:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.1907061165489,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.41547564990715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-8-flash:2ed602cefebb326c",
      "capped_draws": 82,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.2251301931879,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.68634905445009,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:deepseek-deepseek-v4-pro:ff3e59d607a4ac18",
      "capped_draws": 88,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 88,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T04:53:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.2386768969225,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.55105506757531,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 790,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 195,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 258,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 416,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 790,
      "rating_method": "sequential_elo",
      "raw_elo": 1327.1963781961763,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.942780295932366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-8-2-4t-a95b:2caf8bc899f551f3",
      "capped_draws": 111,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 111,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.9171005059115,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.754315907819613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-8-max-0902:565f7de155dcf265",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T12:05:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.539448769024,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.73126434408019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:x-ai-grok-4-7:e9b5a4757d911202",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.0210841058188,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.816492125257373,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 194,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.1517867517532,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.092933810548693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:meta-muse-spark-1-3:b665bb24258fc911",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 133,
      "max_score": null,
      "measured_at": "2026-09-25T05:05:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.071103594417,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.569331169607917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-6-luna:ec8acee7f417cae7",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1258.2643758658196,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.36734015937674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 594,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:z-ai-glm-5-2:51bd53334ebd6ddf",
      "capped_draws": 151,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 249,
      "draws": 151,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 318,
      "max_score": null,
      "measured_at": "2026-09-25T14:08:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 594,
      "rating_method": "sequential_elo",
      "raw_elo": 1225.8204770372306,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.10555575783004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:deepseek-deepseek-v4-flash:b05f493f9c8d196b",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 153,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1223.1473342222712,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.0769225264635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 416,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 148,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 163,
      "draws": 148,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 235,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 416,
      "rating_method": "sequential_elo",
      "raw_elo": 1222.5278976424986,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.894420756801225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 255,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 162,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 255,
      "rating_method": "sequential_elo",
      "raw_elo": 1211.6838207706028,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.309987292783003,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:bytedance-seed-seed-2-0-code:95b26b11b0986534",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-09-25T13:25:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1201.7801698210126,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.505450352817086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 150,
      "max_score": null,
      "measured_at": "2026-09-25T05:56:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1178.7263176583233,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.929347183423104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-7-plus:a3ea745ea8da84ce",
      "capped_draws": 47,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 118,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1164.2895404365493,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.65077416582446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 444,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:cohere-north-mini-code:292c9223f5fe9dd2",
      "capped_draws": 148,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 170,
      "draws": 148,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 253,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 444,
      "rating_method": "sequential_elo",
      "raw_elo": 1148.8249315169192,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.67245084542328,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-1-flash-lite:38c057fa340718ef",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1149.1878789322218,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.578517458993726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 392,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 113,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 113,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 257,
      "max_score": null,
      "measured_at": "2026-09-25T13:25:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 392,
      "rating_method": "sequential_elo",
      "raw_elo": 1103.876733603052,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.926557852896163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:mistralai-mistral-medium-3-5:283b3ca34d89e95f",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 194,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 962.5786552315466,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 5.364102567773256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-fable-5-1:82fc3985d63b4a72",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T06:07:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.2960261882906,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.44955624043591,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-opus-5-5:d1839e51632cc557",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T14:34:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1729.7987285584331,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.90073105067378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-6-astra:24306100b4080f36",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 121,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1708.023682150427,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.02617127882385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 448,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 169,
      "draws": 188,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 448,
      "rating_method": "sequential_elo",
      "raw_elo": 1670.4433465530342,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.505919211020085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 228
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 274,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-8-2-4t-a95b:2caf8bc899f551f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 202,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T06:45:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.2741551137517,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.63268358764324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 372,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 125,
      "draws": 309,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.3153131129332,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.87963566446718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:meta-muse-spark-1-3:b665bb24258fc911",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 197,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T05:15:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.5272225023564,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.693088932871294,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:x-ai-grok-4-7:e9b5a4757d911202",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T14:34:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.5547550320823,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.534713974406596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 294,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 251,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T14:02:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 294,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.4655668165492,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.25613376182144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-6-sol:3e255a0c8d7168aa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.2233710793464,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.009012954450796,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-7-max:79acf3b5f6851440",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 164,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T05:55:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.5097112982878,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.277846845543255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:z-ai-glm-5-3:d95da7acd9780380",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 249,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.4151588117313,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.003603712634062,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:inception-mercury-2-5-preview:ae4030f1f9433705",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 235,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.00281933482,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.830792683984784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:x-ai-grok-4-6:f1d4c61e0708aeae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 201,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.1118446041532,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.478913384343024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 348,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 272,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T07:49:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 348,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.2644727880233,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.95731578720957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-opus-4-5:024e2b4b1f467362",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 192,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T12:33:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.0731425426543,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.849919257531704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 738,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 304,
      "draws": 601,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 113,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 738,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.2107804002305,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.796926219903233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 354,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 296,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 354,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.6825694962292,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.478477269301598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:z-ai-glm-5-3-flash:1c774d2a8faa3025",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-23T12:55:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.7292650442894,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.04578932174765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-5:62529dcffe2e7fae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.100021197292,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.771607546272488,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 237,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T13:55:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 237,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.9517514652248,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.573076409935867,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-4-1:e60d2fa1e7162f32",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 211,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.3652676206952,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.402197288141299,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-6-terra:9663b021bc677328",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 248,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-09-25T06:15:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.192787296789,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.122561741654145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:deepseek-deepseek-v4-1-flash:4de18974b2d2aef7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 87,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T07:40:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.070339189504,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.044306124648847,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:inclusionai-ling-3-0-flash:003df1488166fe5c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 218,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.756171592916,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.596795030322259,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:xiaomi-mimo-v2-6-flash:462b03a9e092439a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T07:23:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.8928882780958,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.524793275000588,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-8-max-0902:565f7de155dcf265",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 76,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.3100352036117,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.176765516320527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 684,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 223,
      "draws": 603,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T04:02:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 683,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.9983873981048,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.07482345464506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 230,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T05:18:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.9943604324985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.053747422410106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:tencent-hy4-preview:9b637fbe1929d4b6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 209,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.8518167627578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.032703602266714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:deepseek-deepseek-v4-flash:b05f493f9c8d196b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 248,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-23T07:28:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.692555699686,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.032375086013085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-4-mini:35d10d5994080add",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 200,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-23T01:24:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.788805327151,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.598572345430599,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 221,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.8164920623371,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.592781159581312,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 454,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-4-nano:44bc85871c51c275",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 160,
      "draws": 380,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 454,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.8231781524264,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.4996181061563,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-6-luna:ec8acee7f417cae7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.591328719958,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.200783051786512,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-opus-4-8:ff1cf2191e10c995",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 182,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.6058873089435,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.918422916272286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 367,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 118,
      "draws": 296,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 367,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.8844189141503,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.898683790605384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:openai-gpt-oss-120b:e4864d083f4798c2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 218,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.8613709181875,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.845665543687444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 266,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T07:23:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.0617383798524,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.754074770690439,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 200,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.974428697136,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.390653049669545,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-7-plus:a3ea745ea8da84ce",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 216,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.5981193259827,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.261021826492382,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5:3f22d9cfc88a4f65",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 120,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T03:24:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.6050675512174,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.227503285322296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:google-gemini-3-1-flash-lite:38c057fa340718ef",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 182,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.0571705946704,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.167843583998868,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 296,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 231,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T05:23:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.7663744997578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.986553392204476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-8-flash:2ed602cefebb326c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 228,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.8842249110578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.785005477286392,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-fable-5:7f6b2a08dddc3940",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 174,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T03:09:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.3571447074532,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.30135369548809,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 654,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:z-ai-glm-5-2:51bd53334ebd6ddf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 245,
      "draws": 583,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 654,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.2757547538108,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.254948532527202,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 674,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 217,
      "draws": 597,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 674,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.7182649446754,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.198390781857146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:minimax-minimax-m3:187f6e5e3d0ad827",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 189,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.9106514889643,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.021854667018928,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:z-ai-glm-5-3-flashx:1240fd0f864b9059",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.9878730014084,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.915683771374111,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 215,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T02:29:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.9765137394702,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.685379769827811,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:google-gemini-3-8-flash:bf006bcd6ccb81c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 198,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.631198326482,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.419192145713985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:xiaomi-mimo-v2-5:8edac6f11a62a0aa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 174,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.6961790820071,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.460914561290655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:google-gemini-3-5-flash:8f1504913d7602c4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 212,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.7833269162336,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 5.490992930648422,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:577995919d91fce3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 180,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T06:15:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.9531513092209,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 4.615901320625215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:mistralai-mistral-medium-3-5:283b3ca34d89e95f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 200,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.3171666207907,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 3.83400018350949,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:xiaomi-mimo-v2-6-pro:a01ac332611439f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.6076019714485,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 3.415118568191135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:tencent-hy3-preview:6e31f3e29e62eb16",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 170,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.6914103410684,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 3.2968970313112287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:nex-agi-nex-n2-pro:b38db13dbc86bdcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 175,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.284192320307,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.10631171802151808,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-fable-5-1:82fc3985d63b4a72",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 48,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T03:10:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1964.727780037505,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.26175197390472,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-6-astra:24306100b4080f36",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 105,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-23T11:59:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1731.0450240140724,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.39056563515839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:tencent-hy4-preview:9b637fbe1929d4b6",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 91,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T13:18:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1645.8815906793627,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.36592552964594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-6-sol:3e255a0c8d7168aa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.5182096935155,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.59414597637835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 288,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:google-gemini-3-8-flash:bf006bcd6ccb81c6",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T13:13:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 287,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.390800807944,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.40886149683821,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:meta-muse-spark-1-3:b665bb24258fc911",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-09-25T12:55:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.5875613105047,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.321044443306036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 128
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 826,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 278,
      "draws": 234,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 276,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 825,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.465897364233,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.96263207896568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 315
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 386,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 144,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 127,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 386,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3910495421942,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.69758041750218,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 154,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-25T13:00:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 395,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.4678989558154,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.5386599849108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:qwen-qwen3-8-2-4t-a95b:2caf8bc899f551f3",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-09-25T14:34:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 267,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.3015602204446,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.833760249546316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:xiaomi-mimo-v2-5:8edac6f11a62a0aa",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 70,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.0560424806201,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.70563172240146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:z-ai-glm-5-3-flash:1c774d2a8faa3025",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 78,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-09-25T04:46:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.0873289037993,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.69837664699844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 140,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T15:05:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.9918204527644,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.60527077189641,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 114,
      "draws": 105,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-09-25T14:34:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.886419174509,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.84294341860225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-opus-5-5:d1839e51632cc557",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T14:34:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.622548247758,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.34311959065729,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:qwen-qwen3-8-max-0902:565f7de155dcf265",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-25T06:08:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.9820140457375,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.06465240673219,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:z-ai-glm-5-3:d95da7acd9780380",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 112,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T05:09:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 289,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.613537643171,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.884063520036406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-4-1:e60d2fa1e7162f32",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T15:52:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.2483969765071,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.72939172603578,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 121,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-09-25T05:01:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.788672542698,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.4132006443893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 390,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 169,
      "max_score": null,
      "measured_at": "2026-09-25T13:13:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 390,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.579434924167,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.401398518164704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:mistralai-mistral-medium-3-5:283b3ca34d89e95f",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T05:33:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.5594912825875,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.358999465512234,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 404,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 139,
      "draws": 104,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 141,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 404,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.7398947124789,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.35563973235182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 159
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:qwen-qwen3-8-flash:2ed602cefebb326c",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 85,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.4048742590476,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.195227382686326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4-mini:35d10d5994080add",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 126,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.666548535275,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.12861045665751,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:deepseek-deepseek-v4-pro-0813:62f039a975dbbc18",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 122,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.0292175090588,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.090831635554785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2040,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 106,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 8,
      "distinct_rated_opponents": 890,
      "draws": 988,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 616,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 2027,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.8573400456446,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.960500358147634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 423
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:minimax-minimax-m3:187f6e5e3d0ad827",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.5735751880513,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.852211767076273,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:x-ai-grok-4-6:f1d4c61e0708aeae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 210,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.6513321364587,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.50159332277543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 454,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 150,
      "draws": 111,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 175,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 454,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.7131334740745,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.57889546605584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 168
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:bytedance-seed-seed-2-0-code:95b26b11b0986534",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 86,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 118,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.1205357785889,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.93788889353827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:meta-muse-glimmer-30b:5f799292ad06c854",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 105,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T07:53:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.400539154845,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.72211236651506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:openai-gpt-oss-120b:e4864d083f4798c2",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T13:00:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.73409700549,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.30577418243054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-5:62529dcffe2e7fae",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T02:18:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.3571775918304,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.006158947241175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 498,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:z-ai-glm-5-2:51bd53334ebd6ddf",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 217,
      "draws": 202,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 183,
      "max_score": null,
      "measured_at": "2026-09-25T07:53:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 498,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.7818056170095,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.263992730844407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.42613636363636465,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:inception-mercury-2-5-preview:ae4030f1f9433705",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 137,
      "max_score": null,
      "measured_at": "2026-09-25T07:24:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 327,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.361021000484,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.88259281471392,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-6-luna:ec8acee7f417cae7",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T06:23:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.2373577118456,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.683992349793055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 253,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 120,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 253,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.7745011547036,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.886410274650494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:z-ai-glm-5-3-flashx:1240fd0f864b9059",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.0109907047743,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.803693368013082,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:xiaomi-mimo-v2-6-flash:462b03a9e092439a",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T14:16:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.5447175645834,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.648906753764663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:deepseek-deepseek-v4-pro:ff3e59d607a4ac18",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T13:18:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1376.0391416548625,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.992442624160834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-fable-5:7f6b2a08dddc3940",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 112,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.2619874653299,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.909155462658255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 304,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "draws": 121,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 118,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 304,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.1594077190425,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.58413890549305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:xiaomi-mimo-v2-6-pro:a01ac332611439f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.8720480178501,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.43721144686283,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:nex-agi-nex-n2-pro:b38db13dbc86bdcd",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 89,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-09-25T12:55:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.2044232021271,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.41165252574357,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-opus-4-5:024e2b4b1f467362",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 86,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-23T18:02:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.539693708129,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.363492385352973,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4-nano:44bc85871c51c275",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.0584808767833,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.184427349708432,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 593,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 219,
      "draws": 232,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 224,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 592,
      "rating_method": "sequential_elo",
      "raw_elo": 1348.950691072303,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.486121890739962,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:deepseek-deepseek-v4-flash:b05f493f9c8d196b",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 97,
      "max_score": null,
      "measured_at": "2026-09-25T07:40:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.0969046013313,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.41588826786613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:deepseek-deepseek-v4-1-flash:4de18974b2d2aef7",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.197069141969,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.61403769326364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-6-terra:9663b021bc677328",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1327.5418566566275,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.392271275872172,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 166,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-09-25T16:03:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.6202852830872,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.097043119894657,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:88820f6e6feb1287",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-09-25T07:53:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.8177773893021,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.796958527790924,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:qwen-qwen3-7-max:79acf3b5f6851440",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T13:18:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1322.0768677527358,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.29269496662492,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:577995919d91fce3",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 81,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1307.8369821715016,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.08692079482323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 179,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-09-25T05:39:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1291.6982265647202,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.358096814846906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 204,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:tencent-hy3-preview:6e31f3e29e62eb16",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-24T21:12:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1291.6821137938018,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.86950861804385,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:google-gemini-3-5-flash:8f1504913d7602c4",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 143,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1261.2317498439854,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.19108200229045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:inclusionai-ling-3-0-flash:003df1488166fe5c",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 143,
      "draws": 137,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 191,
      "max_score": null,
      "measured_at": "2026-09-25T14:16:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.463984346276,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.11442709036542,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5:3f22d9cfc88a4f65",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T13:06:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1147.9746125679014,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 3.1304801359516308,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": null,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 362,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 90,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 251,
      "max_score": null,
      "measured_at": "2026-09-25T13:06:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 362,
      "rating_method": "sequential_elo",
      "raw_elo": 1094.6246645220451,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-6-astra:24306100b4080f36",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1892.848210716588,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.4755448688683,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 182
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-fable-5-1:82fc3985d63b4a72",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1690.6042668268888,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.829742723095954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-opus-5-5:d1839e51632cc557",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1663.7707762059795,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.386745340440996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:z-ai-glm-5-3-flash:1c774d2a8faa3025",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 95,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T06:00:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.7774749008704,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.72860683637134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 438,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 161,
      "draws": 159,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 127,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 438,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.3568685365676,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.879083926934985,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 152
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 412,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 191,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 119,
      "max_score": null,
      "measured_at": "2026-09-25T06:45:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 412,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.0655350180587,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.46384306521568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-opus-4-5:024e2b4b1f467362",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 116,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.031259469797,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.407809820471147,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 858,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 349,
      "draws": 517,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 197,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 857,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.243403122604,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.26787091915678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:qwen-qwen3-8-27b:4712c07305d96aee",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 175,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T06:12:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.9071604016394,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.00270887896228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T05:23:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 209,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.2986589973464,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.19033659038525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:88820f6e6feb1287",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 158,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.7851386586212,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.567731347266125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:xiaomi-mimo-v2-6-pro:a01ac332611439f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.0835524827144,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.435827804187948,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:inception-mercury-2-5-preview:ae4030f1f9433705",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 212,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-24T04:00:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.1967676463596,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.217326577705883,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 880,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 287,
      "draws": 494,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 218,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 873,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.5207476530259,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.726966280556393,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:z-ai-glm-5-3:d95da7acd9780380",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 171,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T15:55:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.468110312634,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.741133901363547,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:z-ai-glm-5-3-flashx:1240fd0f864b9059",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.482847789648,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.713672394721467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:google-gemini-3-8-flash:bf006bcd6ccb81c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 126,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.9671886659755,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.23603223004519,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:qwen-qwen3-8-2-4t-a95b:2caf8bc899f551f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 220,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T03:43:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.07008301429,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.184495234374975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:tencent-hy3-preview:6e31f3e29e62eb16",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 129,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.3635699825543,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.522920844339357,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:deepseek-deepseek-v4-pro-0813:62f039a975dbbc18",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 194,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.2860185393665,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.481794861921347,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 362,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 252,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 362,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.5382030918151,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.374820319063318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 295,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T05:52:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 294,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.1910111845057,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.825149399872654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 207,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.9715983344856,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.67629837390061,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:tencent-hy4-preview:9b637fbe1929d4b6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 175,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.2654462588032,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.37914805089505,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 412,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:xiaomi-mimo-v2-5:8edac6f11a62a0aa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 154,
      "draws": 297,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 412,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.1906957609772,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.142561888673264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:qwen-qwen3-7-plus:a3ea745ea8da84ce",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 170,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 211,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.1114181328019,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.577922253499185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 632,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:z-ai-glm-5-2:51bd53334ebd6ddf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 238,
      "draws": 411,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 137,
      "max_score": null,
      "measured_at": "2026-09-25T15:34:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 632,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.5230611859683,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.527509430585145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:nex-agi-nex-n2-pro:b38db13dbc86bdcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.7803501103617,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.483548530056492,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-4-mini:35d10d5994080add",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 148,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T03:43:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.0070834621893,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.266226481322114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:inclusionai-ling-3-0-flash:003df1488166fe5c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 221,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.8613262957322,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.237152166315024,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 783,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 255,
      "draws": 577,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 147,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 783,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.3135378586849,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.041578305308295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:bytedance-seed-seed-2-0-code:95b26b11b0986534",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 193,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T05:08:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.6582430520918,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.908866749062488,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:x-ai-grok-4-7:e9b5a4757d911202",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2411256233731,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.846953534414173,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-6-luna:ec8acee7f417cae7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.4460367748802,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.335284250370272,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:meta-muse-glimmer-30b:5f799292ad06c854",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 204,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T13:55:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.2969571565277,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.298673684741303,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-6-terra:9663b021bc677328",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 172,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T04:29:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.8981458755488,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.870289650425716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:google-gemini-3-5-flash:8f1504913d7602c4",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 100,
      "draws": 271,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.7181118977787,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.82847960102021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:deepseek-deepseek-v4-pro:ff3e59d607a4ac18",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 194,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.3731814594128,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.507335399739189,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 175,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.6914723964546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.419894829106827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:meta-muse-spark-1-3:b665bb24258fc911",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 155,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T04:07:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.0738254576515,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.707425405221867,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-5:62529dcffe2e7fae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 136,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 209,
      "rating_method": "sequential_elo",
      "raw_elo": 1415.7204330427496,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.178420752709116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:qwen-qwen3-8-flash:2ed602cefebb326c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 185,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.9387944129749,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.978147131546923,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:google-gemma-4-31b-it:b471a27d319d0e3f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 161,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.301181523511,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.918261292629804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 217,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.2999660185344,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.66110569393519,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 294,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:x-ai-grok-4-6:f1d4c61e0708aeae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 194,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 294,
      "rating_method": "sequential_elo",
      "raw_elo": 1404.529445312924,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.14033355812917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-6-sol:3e255a0c8d7168aa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.9916701005964,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.969256362592526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:mistralai-mistral-medium-3-5:283b3ca34d89e95f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 117,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-09-25T15:34:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 231,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.8619413155873,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.439966470700094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:deepseek-deepseek-v4-1-flash:4de18974b2d2aef7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.931015786824,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.271801424400126,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-opus-4-8:ff1cf2191e10c995",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 164,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.4656687451038,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.320747401269687,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 458,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 165,
      "draws": 299,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 456,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.5497321724583,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.310346249205763,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-fable-5:7f6b2a08dddc3940",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 189,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 304,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.971331282551,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.302860861924804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 364,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 279,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T12:48:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 364,
      "rating_method": "sequential_elo",
      "raw_elo": 1385.504166709032,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.623581070029456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 367,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 126,
      "max_score": null,
      "measured_at": "2026-09-25T05:23:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 367,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.7459540811358,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.220151455961185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 378,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 241,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 378,
      "rating_method": "sequential_elo",
      "raw_elo": 1382.1888608397242,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.182072363962202,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-4-1:e60d2fa1e7162f32",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 162,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.6441886130692,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.9862813021302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:qwen-qwen3-8-max-0902:565f7de155dcf265",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T05:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.2341818563582,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 2.3421974844057343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-6-astra:24306100b4080f36",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T01:55:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 2248.649683482002,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 96.36396331063021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 220
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 243,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 243,
      "rating_method": "sequential_elo",
      "raw_elo": 2148.940389501246,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 90.1443955387162,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 225
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-fable-5-1:82fc3985d63b4a72",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 2124.9151167812875,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 88.63477864319661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 229
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 406,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 164,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 406,
      "rating_method": "sequential_elo",
      "raw_elo": 2118.6704565869495,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 88.08721167316827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 375
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-opus-5-5:d1839e51632cc557",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1979.0551477968836,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 78.29416493729859,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-6-sol:3e255a0c8d7168aa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1799.3800322438697,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.0440325823212,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-fable-5:7f6b2a08dddc3940",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1766.2684251914866,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.07585031971833,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 158
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-8-max-0902:565f7de155dcf265",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T05:11:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1677.695635179499,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.317058041724536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 493,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 159,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 199,
      "max_score": null,
      "measured_at": "2026-09-25T15:55:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 493,
      "rating_method": "sequential_elo",
      "raw_elo": 1650.0349636228016,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.20674314072263,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 294
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 410,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 195,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 410,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.431668197681,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.41476958488925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 215
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 148,
      "max_score": null,
      "measured_at": "2026-09-25T14:04:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 328,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.948185472631,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.4119151014792,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 286,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:z-ai-glm-5-3:d95da7acd9780380",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 127,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.5939742462938,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.33934475189269,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 159
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 903,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 291,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 420,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 903,
      "rating_method": "sequential_elo",
      "raw_elo": 1534.9083210515219,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.905912358610884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 483
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 180,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:88820f6e6feb1287",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T06:23:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.422857529501,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.8801788071995,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 107
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 828,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 357,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 391,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 828,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.1538799153157,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.393316198139864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 437
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:xiaomi-mimo-v2-6-flash:462b03a9e092439a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.4622565590478,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.210868821751404,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemini-3-8-flash:bf006bcd6ccb81c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 156,
      "max_score": null,
      "measured_at": "2026-09-23T19:09:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.481048378976,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.14934593047246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 404,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 176,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 404,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.3744994196975,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.86049443053713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 228
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 399,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 130,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 204,
      "max_score": null,
      "measured_at": "2026-09-25T03:31:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 399,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.0032310977772,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.325543397766175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:x-ai-grok-4-6:f1d4c61e0708aeae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 149,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.4136462064191,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.202255327441996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:deepseek-deepseek-v4-flash:b05f493f9c8d196b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 107,
      "max_score": null,
      "measured_at": "2026-09-25T05:32:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.4080298081694,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.77498312108857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:tencent-hy4-preview:9b637fbe1929d4b6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 167,
      "max_score": null,
      "measured_at": "2026-09-25T05:03:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 328,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.652345603618,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.5444682336586,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:z-ai-glm-5-3-flashx:1240fd0f864b9059",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.7087197710289,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.17104342624617,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-5:62529dcffe2e7fae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T03:41:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.7349393810994,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.045069424600065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 190,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-opus-4-5:024e2b4b1f467362",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-09-25T06:31:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.0388634204105,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.127369719800235,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 109
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-6-luna:ec8acee7f417cae7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.0240754278334,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.74933846094135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 418,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 162,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 193,
      "max_score": null,
      "measured_at": "2026-09-25T12:49:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 418,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.02865773044,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.950499952815655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 225
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5:3f22d9cfc88a4f65",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T15:55:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.1946489205093,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.01346355780045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": null,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-7-plus:a3ea745ea8da84ce",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.7681750856045,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.55040400948236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:meta-muse-spark-1-3:b665bb24258fc911",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 129,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 162,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.4470525560284,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.108249106768326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:z-ai-glm-5-3-flash:1c774d2a8faa3025",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 125,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.8716949943114,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.264060881669415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-7-max:79acf3b5f6851440",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T03:41:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.0131556037793,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.223683029145114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:x-ai-grok-4-7:e9b5a4757d911202",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.565203529387,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.42296831994141,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:deepseek-deepseek-v4-pro:ff3e59d607a4ac18",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.5318824887702,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.55572744176421,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 388,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 233,
      "max_score": null,
      "measured_at": "2026-09-25T15:41:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 384,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.2550007761117,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.91922843039871,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 151
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:inception-mercury-2-5-preview:ae4030f1f9433705",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1326.0360262339282,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.37213841472128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 616,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:z-ai-glm-5-2:51bd53334ebd6ddf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 267,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 388,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 616,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.8835294807768,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.676359538540034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 228
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:xiaomi-mimo-v2-6-pro:a01ac332611439f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-25T05:13:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.7719737993527,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.46449004717655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 552,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:xiaomi-mimo-v2-5:8edac6f11a62a0aa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 228,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 354,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 552,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.6122520189124,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.88953366402243,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 198
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:deepseek-deepseek-v4-1-flash:4de18974b2d2aef7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1274.647621010709,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.969178885975495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:nex-agi-nex-n2-pro:b38db13dbc86bdcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 127,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 202,
      "rating_method": "sequential_elo",
      "raw_elo": 1258.620863230517,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.9241439224965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:minimax-minimax-m3:187f6e5e3d0ad827",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 138,
      "max_score": null,
      "measured_at": "2026-09-25T07:32:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1256.4377579120328,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.89005402357793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-8-2-4t-a95b:2caf8bc899f551f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1255.5273945881124,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.81799644348555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 310,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 213,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 310,
      "rating_method": "sequential_elo",
      "raw_elo": 1236.6531644054721,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.88038109999295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 221,
      "max_score": null,
      "measured_at": "2026-09-25T04:02:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1211.2843177396303,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.300886532170168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 158,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 259,
      "max_score": null,
      "measured_at": "2026-09-25T01:46:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1214.094123317484,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.100848093492324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-opus-4-8:ff1cf2191e10c995",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 135,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1177.1039837496114,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.773211795209818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:577995919d91fce3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 135,
      "max_score": null,
      "measured_at": "2026-09-25T12:48:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1173.139299796228,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.566789813099383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-8-flash:2ed602cefebb326c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 196,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1165.0488835259146,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.222283900175665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:mistralai-mistral-medium-3-5:283b3ca34d89e95f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 191,
      "max_score": null,
      "measured_at": "2026-09-25T14:16:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1119.0368805636974,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.23037696584976,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:tencent-hy3-preview:6e31f3e29e62eb16",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 183,
      "max_score": null,
      "measured_at": "2026-09-25T02:18:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1099.7712464212616,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.117792770251928,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-4-mini:35d10d5994080add",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 140,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1070.9035033771586,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.019261559659135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:openai-gpt-oss-120b:e4864d083f4798c2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 179,
      "max_score": null,
      "measured_at": "2026-09-25T05:13:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1058.036358089146,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.396389762012983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:bytedance-seed-seed-2-0-code:95b26b11b0986534",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 186,
      "max_score": null,
      "measured_at": "2026-09-25T13:28:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1047.1995225663443,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.721197658478708,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemini-3-5-flash:8f1504913d7602c4",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 283,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1049.0451834640826,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.505627298833392,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.4376202060078436,
      "unilateral_faults": null,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemma-4-31b-it:b471a27d319d0e3f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 164,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 996.4721889908689,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 17.441769674969127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 418,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 158,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 327,
      "max_score": null,
      "measured_at": "2026-09-25T07:49:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 414,
      "rating_method": "sequential_elo",
      "raw_elo": 989.1863512819759,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.978770000497704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 4,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-4-1:e60d2fa1e7162f32",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 166,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 983.6847562803387,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.636523889428613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-4-nano:44bc85871c51c275",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 151,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 334,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 945.0674090073451,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.160401525981356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemini-3-1-flash-lite:38c057fa340718ef",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 143,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 945.7882412819017,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.077395343984001,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 818,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 258,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 714,
      "max_score": null,
      "measured_at": "2026-09-25T04:49:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 818,
      "rating_method": "sequential_elo",
      "raw_elo": 931.6901172244059,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.859889298232568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 222,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 829.0826803647128,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.993147556840411,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:meta-muse-glimmer-30b:5f799292ad06c854",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 213,
      "max_score": null,
      "measured_at": "2026-09-25T01:29:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 818.5249709768012,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.328311136424571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 218,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 2126.4040981564867,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 88.30380211671529,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-fable-5-1:82fc3985d63b4a72",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1928.728046457806,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.44706783220323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 177
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-6-astra:24306100b4080f36",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T03:45:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1875.2559958586826,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 73.19124617557102,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-8-max-0902:565f7de155dcf265",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T07:31:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1865.4579020509198,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.7714779302936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:x-ai-grok-4-7:e9b5a4757d911202",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T12:47:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1860.3173121974187,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.24448433375413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-fable-5:7f6b2a08dddc3940",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T05:00:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1834.422702351709,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.71820370255907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemini-3-8-flash:bf006bcd6ccb81c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1798.6291417013492,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.57629933967782,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-opus-5-5:d1839e51632cc557",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1813.795133998968,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.40320390202572,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-6-sol:3e255a0c8d7168aa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1725.945749179493,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.21642923019296,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 336,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 119,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 336,
      "rating_method": "sequential_elo",
      "raw_elo": 1705.2403347677614,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.18239982783971,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-8-2-4t-a95b:2caf8bc899f551f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1626.900963741159,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.38797062519658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:z-ai-glm-5-3-flashx:1240fd0f864b9059",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.1284190954095,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.68992736691443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:deepseek-deepseek-v4-pro-0813:62f039a975dbbc18",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 138,
      "max_score": null,
      "measured_at": "2026-09-25T06:04:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.531598919758,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.44640162344343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 433,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 143,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 173,
      "max_score": null,
      "measured_at": "2026-09-25T04:49:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 433,
      "rating_method": "sequential_elo",
      "raw_elo": 1603.9204548597472,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.21913279521076,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 249
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 336,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-8-flash:2ed602cefebb326c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 140,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 336,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.2344503904574,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.77974293719396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 186
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 336,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:deepseek-deepseek-v4-flash:b05f493f9c8d196b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 137,
      "max_score": null,
      "measured_at": "2026-09-25T07:15:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 336,
      "rating_method": "sequential_elo",
      "raw_elo": 1587.5047468720559,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.07127974669768,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 934,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 298,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 410,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 934,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.267097460467,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.50461528693461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 513
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:xiaomi-mimo-v2-6-flash:462b03a9e092439a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.6492842445664,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.11187823957251,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:z-ai-glm-5-3:d95da7acd9780380",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 162,
      "max_score": null,
      "measured_at": "2026-09-25T13:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.2354984855863,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.263519135398994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 152
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:xiaomi-mimo-v2-6-pro:a01ac332611439f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.1032066491546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.486251574367515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-4-1:e60d2fa1e7162f32",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.3995689204392,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.838972097614196,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 124
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 272,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:meta-muse-spark-1-3:b665bb24258fc911",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 131,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.2174451164249,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.149913347085835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 488,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 148,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 230,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 488,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.5641181916208,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.87613336669571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 214
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 489,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 151,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 247,
      "max_score": null,
      "measured_at": "2026-09-25T04:55:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 489,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.8370706263297,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.531340418862875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 634,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:z-ai-glm-5-2:51bd53334ebd6ddf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 242,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 267,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 634,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.6630422095277,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.221030432322465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 309
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:tencent-hy4-preview:9b637fbe1929d4b6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.4170921444886,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.71005822548814,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-opus-4-8:ff1cf2191e10c995",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 76,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-09-25T02:56:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 226,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.4483679946977,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.27096420079218,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 940,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 376,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 527,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 940,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.4377306941285,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.47240899941553,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 388
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 494,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 157,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 256,
      "max_score": null,
      "measured_at": "2026-09-25T05:00:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 494,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.9002702101798,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.52073030334479,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 206
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemini-3-5-flash:8f1504913d7602c4",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 254,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 456,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.911070005575,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.893913436362745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 192
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:z-ai-glm-5-3-flash:1c774d2a8faa3025",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 183,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.963785463048,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.867686109837216,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 422,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-4-nano:44bc85871c51c275",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 161,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 217,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 422,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.9098744914804,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.52477509866081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 204
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 426,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 207,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 426,
      "rating_method": "sequential_elo",
      "raw_elo": 1357.2698586081942,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.31219893783358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 198
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-6-terra:9663b021bc677328",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 137,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.2974637325274,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.861028222502206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-opus-4-5:024e2b4b1f467362",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.0757812157685,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.708782628285576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 94
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 486,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 167,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 258,
      "max_score": null,
      "measured_at": "2026-09-25T15:10:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.7431065972619,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.60041525625513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 192
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:577995919d91fce3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 122,
      "max_score": null,
      "measured_at": "2026-09-25T05:00:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.8761528680536,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.26936162900415,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 630,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:xiaomi-mimo-v2-5:8edac6f11a62a0aa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 224,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 355,
      "max_score": null,
      "measured_at": "2026-09-25T06:44:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 630,
      "rating_method": "sequential_elo",
      "raw_elo": 1253.0393623188336,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.53171599477679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 269
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-4-mini:35d10d5994080add",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 125,
      "max_score": null,
      "measured_at": "2026-09-25T14:36:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.0923632699235,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.9978767970118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemini-3-1-flash-lite:38c057fa340718ef",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1200.9451326757076,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.38410669171022,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 176,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1161.472768750128,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.171288882691577,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:deepseek-deepseek-v4-1-flash:4de18974b2d2aef7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1177.7559335408441,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.106273873269323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 816,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 254,
      "draws": 85,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 555,
      "max_score": null,
      "measured_at": "2026-09-25T15:10:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 816,
      "rating_method": "sequential_elo",
      "raw_elo": 1147.8027589015026,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.63511971413311,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 176
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 267,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 203,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 267,
      "rating_method": "sequential_elo",
      "raw_elo": 1149.403958214884,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.450673929819136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-6-luna:ec8acee7f417cae7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1157.797087354043,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.928158563781658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 162,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1136.8956765035823,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.621128644913895,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 392,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 285,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 392,
      "rating_method": "sequential_elo",
      "raw_elo": 1098.203423189367,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.615301347660477,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 338,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 256,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 338,
      "rating_method": "sequential_elo",
      "raw_elo": 1093.6370561762542,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.246018169613286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:inception-mercury-2-5-preview:ae4030f1f9433705",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 171,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1093.5609104681846,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.977589553967935,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemma-4-31b-it:b471a27d319d0e3f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 152,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1089.7617560473384,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.706276161565984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:mistralai-mistral-medium-3-5:283b3ca34d89e95f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 187,
      "max_score": null,
      "measured_at": "2026-09-25T06:09:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1081.280252900736,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.249093186396834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:bytedance-seed-seed-2-0-code:95b26b11b0986534",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 191,
      "max_score": null,
      "measured_at": "2026-09-25T05:30:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1079.7568802673843,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.18259900050788,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-7-max:79acf3b5f6851440",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 169,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1057.325050187689,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.775390810505247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 360,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 279,
      "max_score": null,
      "measured_at": "2026-09-25T00:02:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 360,
      "rating_method": "sequential_elo",
      "raw_elo": 1049.1009470500528,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.59669007853958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:88820f6e6feb1287",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 149,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1054.246550419755,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.49982887875695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:x-ai-grok-4-6:f1d4c61e0708aeae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 228,
      "max_score": null,
      "measured_at": "2026-09-25T01:00:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1044.5694235124092,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.142938274891982,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 192,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1034.0499364772634,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.446247803353653,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-7-plus:a3ea745ea8da84ce",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 174,
      "max_score": null,
      "measured_at": "2026-09-25T13:25:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 983.0303224250979,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.267003258236837,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:nex-agi-nex-n2-pro:b38db13dbc86bdcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 173,
      "max_score": null,
      "measured_at": "2026-09-25T15:24:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 942.5334712146507,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.768455567867043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 492,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:inclusionai-ling-3-0-flash:003df1488166fe5c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 162,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 408,
      "max_score": null,
      "measured_at": "2026-09-25T15:10:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 851.2838770926161,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.38300416268924,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-6-astra:24306100b4080f36",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T06:08:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 2251.6025571214686,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 97.38715231698653,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 245
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-fable-5-1:82fc3985d63b4a72",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1996.5610215766385,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 80.28043626941351,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 216
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-opus-5-5:d1839e51632cc557",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 2004.3585172896226,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 79.85364697365718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1925.7828444100635,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.48747960512179,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 196
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:z-ai-glm-5-3:d95da7acd9780380",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 96,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1812.148293499103,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.95978288951696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 166
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 129,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T07:53:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 396,
      "rating_method": "sequential_elo",
      "raw_elo": 1795.5455136114233,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.15463779430945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 264
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:nex-agi-nex-n2-pro:b38db13dbc86bdcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 82,
      "max_score": null,
      "measured_at": "2026-09-23T15:27:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1760.9349440620415,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 64.55194498926986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 275,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 96,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 275,
      "rating_method": "sequential_elo",
      "raw_elo": 1741.9329256680928,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.29321035518914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:z-ai-glm-5-3-flash:1c774d2a8faa3025",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T12:54:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1740.5070985519903,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.151925655306094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 340,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-fable-5:7f6b2a08dddc3940",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 140,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 340,
      "rating_method": "sequential_elo",
      "raw_elo": 1684.7963698508281,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.62572675932049,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 200
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-6-sol:3e255a0c8d7168aa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1677.4254768113583,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.99178835476464,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:z-ai-glm-5-3-flashx:1240fd0f864b9059",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.843640585245,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.16570558834896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 874,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 286,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 343,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 874,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.2314652141795,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.66854839969095,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 531
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:qwen-qwen3-7-max:79acf3b5f6851440",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1627.6300514217016,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.45085414085405,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 288,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:qwen-qwen3-8-2-4t-a95b:2caf8bc899f551f3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.1985659619909,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.937997689218676,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 142
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 881,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 288,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 413,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 877,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.7165694005175,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.66524674768772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 464
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-4-1:e60d2fa1e7162f32",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-22T19:29:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.7906560666256,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.413228051643856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 352,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:x-ai-grok-4-6:f1d4c61e0708aeae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 147,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 155,
      "max_score": null,
      "measured_at": "2026-09-25T05:19:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.0956228971488,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.74075816746098,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 197
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:577995919d91fce3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.46710023982,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.29932137115699,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 792,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:z-ai-glm-5-2:51bd53334ebd6ddf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 310,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 399,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 792,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.4406805378987,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.703813687928275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 393
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:x-ai-grok-4-7:e9b5a4757d911202",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T05:48:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.942734019108,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.04669634247453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-opus-4-8:ff1cf2191e10c995",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T06:23:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.779451138306,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.77403884472038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 346,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:deepseek-deepseek-v4-pro:ff3e59d607a4ac18",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 144,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 153,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 346,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.90708301305,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.02962894499428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 193
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 506,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 171,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 276,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 498,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.8511196698983,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.43267997067568,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 222
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5:3f22d9cfc88a4f65",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 85,
      "max_score": null,
      "measured_at": "2026-09-25T04:49:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.0583806015484,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.25132030051264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-5:62529dcffe2e7fae",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-09-25T12:17:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.3414175278592,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.021359823488645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 274,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:tencent-hy4-preview:9b637fbe1929d4b6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 145,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.8567751138708,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.508357711216625,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:google-gemini-3-5-flash:8f1504913d7602c4",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 232,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 436,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.0216338505575,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.74380662152359,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 204
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:xiaomi-mimo-v2-6-pro:a01ac332611439f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.2346624876882,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.3468858005456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 954,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 399,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 560,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 954,
      "rating_method": "sequential_elo",
      "raw_elo": 1358.9488067831278,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.724790002335574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 394
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 437,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 224,
      "max_score": null,
      "measured_at": "2026-09-25T06:12:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 437,
      "rating_method": "sequential_elo",
      "raw_elo": 1352.0100444121738,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.492528172236426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 213
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 412,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 210,
      "max_score": null,
      "measured_at": "2026-09-25T15:14:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 412,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.8705284872053,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.04284479501129,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:meta-muse-spark-1-3:b665bb24258fc911",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 135,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1343.1757005337963,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.51558912753892,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:xiaomi-mimo-v2-6-flash:462b03a9e092439a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1356.4235677106053,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.40173017070555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 394,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 234,
      "max_score": null,
      "measured_at": "2026-09-25T07:40:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 394,
      "rating_method": "sequential_elo",
      "raw_elo": 1327.433947126968,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.77746607761612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:google-gemini-3-8-flash:bf006bcd6ccb81c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 152,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1327.3203385304666,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.51374807836425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 126
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 235,
      "max_score": null,
      "measured_at": "2026-09-25T15:14:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.3770693573304,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.279940763003445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:qwen-qwen3-8-max-0902:565f7de155dcf265",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1340.6210604790344,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.25966512394811,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 166,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.9434304636081,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.8496179823456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-opus-4-5:024e2b4b1f467362",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.565874028835,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.79269831952821,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:openai-gpt-oss-120b:e4864d083f4798c2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 170,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.1689877013564,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.706610269607616,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 514,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 182,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 301,
      "max_score": null,
      "measured_at": "2026-09-25T15:14:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 514,
      "rating_method": "sequential_elo",
      "raw_elo": 1296.3619056884113,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.37480073077782,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 213
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 420,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 144,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 279,
      "max_score": null,
      "measured_at": "2026-09-25T02:35:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 420,
      "rating_method": "sequential_elo",
      "raw_elo": 1284.8616505679433,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.966502103404125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 416,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 130,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 270,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 416,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.6530130186823,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.41009124407256,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 146
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-6-terra:9663b021bc677328",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 133,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 222,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 326,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.1709531370514,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.141063215171016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 422,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 133,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 265,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 422,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.8962343284793,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.03360459011067,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 157
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:bytedance-seed-seed-2-0-code:95b26b11b0986534",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 163,
      "max_score": null,
      "measured_at": "2026-09-25T12:53:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1265.6389751628028,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.350179723882725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:meta-muse-glimmer-30b:5f799292ad06c854",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 175,
      "max_score": null,
      "measured_at": "2026-09-25T15:41:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1252.2663514681587,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.447809314101196,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:minimax-minimax-m3:187f6e5e3d0ad827",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 164,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1207.8219281213146,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.40392435260142,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:deepseek-deepseek-v4-1-flash:4de18974b2d2aef7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1221.2912021064592,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.29044391522753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 168,
      "max_score": null,
      "measured_at": "2026-09-25T13:13:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1188.52176640002,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.11038906658177,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:deepseek-deepseek-v4-pro-0813:62f039a975dbbc18",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 188,
      "max_score": null,
      "measured_at": "2026-09-25T06:00:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1158.6186237992895,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.165172475622438,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 470,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:xiaomi-mimo-v2-5:8edac6f11a62a0aa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 171,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 330,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 468,
      "rating_method": "sequential_elo",
      "raw_elo": 1155.2246707720728,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.83569370000309,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 138
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 470,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:cohere-north-mini-code:292c9223f5fe9dd2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 161,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 350,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 466,
      "rating_method": "sequential_elo",
      "raw_elo": 1116.574474382739,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.234030707551817,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 4,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 280,
      "max_score": null,
      "measured_at": "2026-09-25T02:22:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1102.7019365005071,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.616837033914027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-4-nano:44bc85871c51c275",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 188,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1101.7822101593483,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.33044730875999,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:deepseek-deepseek-v4-flash:b05f493f9c8d196b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 204,
      "max_score": null,
      "measured_at": "2026-09-25T06:12:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1081.8628498304731,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.001881317402578,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:qwen-qwen3-8-flash:2ed602cefebb326c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 241,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1044.8864063083101,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.55490280256513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:google-gemma-4-31b-it:b471a27d319d0e3f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 186,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1006.15809921059,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.829926370851808,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:qwen-qwen3-7-plus:a3ea745ea8da84ce",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 202,
      "max_score": null,
      "measured_at": "2026-09-25T04:13:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 988.9738841198142,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.715188962171446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:88820f6e6feb1287",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 80,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 192,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 874.362902625652,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 4.923730589416949,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:google-gemini-3-1-flash-lite:38c057fa340718ef",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 188,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 802.9446684034115,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.08310002118024254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-4-mini:35d10d5994080add",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 224,
      "max_score": null,
      "measured_at": "2026-09-25T00:20:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 799.04601452757,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 418,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 418,
      "rating_method": "sequential_elo",
      "raw_elo": 2154.9857455992246,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 88.12366220504157,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 394
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-fable-5-1:82fc3985d63b4a72",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 2008.9984085163755,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.66390549772187,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 234
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-fable-5:7f6b2a08dddc3940",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-09-25T14:08:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1931.433559611224,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.75317794233399,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 208
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 374,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T14:18:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 374,
      "rating_method": "sequential_elo",
      "raw_elo": 1885.03147903014,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.54145227969542,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 276
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-6-astra:24306100b4080f36",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T14:04:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1881.6480911845326,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.96573216582014,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 193
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-4-8:ff1cf2191e10c995",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T05:43:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1869.4824195444983,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.98085473100755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 189
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-4-5:024e2b4b1f467362",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1864.763508359985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.59804006842714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 414,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 148,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 414,
      "rating_method": "sequential_elo",
      "raw_elo": 1832.3904048949994,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.62192583535994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 327
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-6-sol:3e255a0c8d7168aa",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1813.07111891493,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.76313979266979,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 86
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-8-2-4t-a95b:2caf8bc899f551f3",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.7833446010702,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.087876316969584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 205
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.5393730240885,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.97193472120926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemini-3-8-flash:bf006bcd6ccb81c6",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1771.2634784422758,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.62650606194331,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 176
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:xiaomi-mimo-v2-6-pro:a01ac332611439f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Pro",
      "model_slug": "xiaomi-mimo-v2-6-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1765.1638806175774,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.09922504114827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 688,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 235,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 160,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 688,
      "rating_method": "sequential_elo",
      "raw_elo": 1724.7477595332903,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.276783376822266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 475
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:x-ai-grok-4-7:e9b5a4757d911202",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T12:33:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1715.9358880058066,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.21796242891374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 382,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 179,
      "max_score": null,
      "measured_at": "2026-09-25T14:38:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 382,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.4853319623594,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.256103303349285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 194
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-5-5:d1839e51632cc557",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 112,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 85,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.3607902781105,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.166191917522255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.335874651846873,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:minimax-minimax-m3:187f6e5e3d0ad827",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 113,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.443424206279,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.47095379427678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 120
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 488,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4-nano:44bc85871c51c275",
      "capped_draws": 195,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 167,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 129,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 488,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.4996393916958,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.53835062072972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 356,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 156,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 156,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-09-25T07:15:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 356,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.7341140338356,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.61357997419428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 406,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 156,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 156,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 126,
      "max_score": null,
      "measured_at": "2026-09-25T06:57:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 406,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.6770910024586,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.87599461687681,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 124
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 764,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:z-ai-glm-5-2:51bd53334ebd6ddf",
      "capped_draws": 343,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 290,
      "draws": 343,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 208,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 764,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.7614207528857,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.631247759725134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 213
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-terra:9663b021bc677328",
      "capped_draws": 189,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 139,
      "draws": 189,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-09-25T13:20:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 328,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.564014090361,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.99078251203825,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:x-ai-grok-4-6:f1d4c61e0708aeae",
      "capped_draws": 213,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 161,
      "draws": 213,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 107,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.7735880738578,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.691823305388205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5:3f22d9cfc88a4f65",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 127,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T14:04:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1390.5429142518308,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.342414005937076,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:tencent-hy3-preview:6e31f3e29e62eb16",
      "capped_draws": 205,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-09-25T06:05:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.0274390867012,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.84561016247001,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-4-1:e60d2fa1e7162f32",
      "capped_draws": 170,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 170,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.142480613769,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.334237110128832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-8-max-0902:565f7de155dcf265",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.2444001226727,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.045603337595335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 218,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 218,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-22T11:44:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.0281060038924,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.744757653812606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:mistralai-mistral-medium-3-5:283b3ca34d89e95f",
      "capped_draws": 192,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 192,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T05:41:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.2196973298408,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.16614110712482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 426,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 279,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 279,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 126,
      "max_score": null,
      "measured_at": "2026-09-25T07:23:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 426,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.3692796598912,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.904305056012785,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 920,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 569,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 305,
      "draws": 569,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 292,
      "max_score": null,
      "measured_at": "2026-09-25T14:03:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 920,
      "rating_method": "sequential_elo",
      "raw_elo": 1332.1302501376986,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.70917520967793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-8-27b:4712c07305d96aee",
      "capped_draws": 221,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 221,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-09-25T05:43:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 328,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.439317034092,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.6290352177258,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 296,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:meta-muse-spark-1-3:b665bb24258fc911",
      "capped_draws": 202,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 202,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1333.7086722472022,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.485658092588114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:deepseek-deepseek-v4-pro-0813:62f039a975dbbc18",
      "capped_draws": 205,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.8407636259985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.074351406838364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 304,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-8-flash:2ed602cefebb326c",
      "capped_draws": 203,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Flash",
      "model_slug": "qwen-qwen3-8-flash",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 304,
      "rating_method": "sequential_elo",
      "raw_elo": 1321.2787153819802,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.565120302446235,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 403,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 252,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 133,
      "draws": 252,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 136,
      "max_score": null,
      "measured_at": "2026-09-25T06:15:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 403,
      "rating_method": "sequential_elo",
      "raw_elo": 1317.5766304670988,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.51205331176168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-5:62529dcffe2e7fae",
      "capped_draws": 169,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 169,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T15:10:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1322.3451540972053,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.444795053368917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 532,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 420,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 222,
      "draws": 420,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-09-25T05:56:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 532,
      "rating_method": "sequential_elo",
      "raw_elo": 1319.8843881862263,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.339256932464274,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 532,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 393,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 192,
      "draws": 393,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 113,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 532,
      "rating_method": "sequential_elo",
      "raw_elo": 1319.3611201675367,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.298898663270595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4-mini:35d10d5994080add",
      "capped_draws": 171,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 171,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.1696200624187,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.23875235015678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:nex-agi-nex-n2-pro:b38db13dbc86bdcd",
      "capped_draws": 199,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 199,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.7216823557662,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.208092923512243,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:88820f6e6feb1287",
      "capped_draws": 168,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 168,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T13:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1319.3025413145217,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.181292624255057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 876,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 600,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 267,
      "draws": 600,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 243,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 876,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.1806123108736,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.086761769650685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 608,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:inclusionai-ling-3-0-flash:003df1488166fe5c",
      "capped_draws": 437,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 194,
      "draws": 437,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 141,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 606,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.988025781403,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.0086745606863,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:bytedance-seed-seed-2-0-code:95b26b11b0986534",
      "capped_draws": 191,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 191,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-09-25T06:15:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.029726376838,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.681044835220536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 542,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 382,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 187,
      "draws": 382,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 141,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 542,
      "rating_method": "sequential_elo",
      "raw_elo": 1309.5085507135805,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.568927521142058,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:meta-muse-glimmer-30b:5f799292ad06c854",
      "capped_draws": 193,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 193,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T07:01:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1309.115476003638,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.50068426102481,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 288,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:tencent-hy4-preview:9b637fbe1929d4b6",
      "capped_draws": 193,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 193,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1305.355782588245,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.308602589729603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:deepseek-deepseek-v4-pro:ff3e59d607a4ac18",
      "capped_draws": 184,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 184,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T03:22:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1306.1903913845374,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.278583142445555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:cohere-north-mini-code:292c9223f5fe9dd2",
      "capped_draws": 202,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 202,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1305.0370526777124,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.265561771241,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemini-3-5-flash:8f1504913d7602c4",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 110,
      "draws": 309,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 436,
      "rating_method": "sequential_elo",
      "raw_elo": 1308.4865269685897,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.25146892901356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": null,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemma-4-31b-it:b471a27d319d0e3f",
      "capped_draws": 176,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 176,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T15:10:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1305.335449504434,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.234910904260282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:577995919d91fce3",
      "capped_draws": 146,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 146,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-23T15:51:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.6831239572457,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.6593423326237,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:deepseek-deepseek-v4-1-flash:4de18974b2d2aef7",
      "capped_draws": 68,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1309.6429151589853,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.484542801549498,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-6-luna:ec8acee7f417cae7",
      "capped_draws": 57,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1306.792176313163,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.372054943804372,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-7-max:79acf3b5f6851440",
      "capped_draws": 162,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 89,
      "draws": 162,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1283.4622351785426,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.587850473736427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 408,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 284,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 284,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-09-25T05:30:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 408,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.7831903055633,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.499809680072865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:z-ai-glm-5-3-flashx:1240fd0f864b9059",
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1279.1318672273992,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.111374859763473,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:openai-gpt-oss-120b:e4864d083f4798c2",
      "capped_draws": 194,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 194,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1262.3682714492068,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.96542035285595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 476,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:xiaomi-mimo-v2-5:8edac6f11a62a0aa",
      "capped_draws": 305,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 182,
      "draws": 305,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 168,
      "max_score": null,
      "measured_at": "2026-09-25T15:33:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 476,
      "rating_method": "sequential_elo",
      "raw_elo": 1251.8248335378,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.06578872946892,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:xiaomi-mimo-v2-6-flash:462b03a9e092439a",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.6-Flash",
      "model_slug": "xiaomi-mimo-v2-6-flash",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1224.9878973868924,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.135717854305447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:z-ai-glm-5-3:d95da7acd9780380",
      "capped_draws": 155,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 155,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-09-25T14:17:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1202.2009674708343,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.38984780565305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:deepseek-deepseek-v4-flash:b05f493f9c8d196b",
      "capped_draws": 133,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 133,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1201.3201181817356,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.337046587683027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 286,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:z-ai-glm-5-3-flash:1c774d2a8faa3025",
      "capped_draws": 144,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 144,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 136,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1149.9019136121656,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.498805673082217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 348,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 267,
      "max_score": null,
      "measured_at": "2026-09-25T07:15:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 348,
      "rating_method": "sequential_elo",
      "raw_elo": 1110.857285273001,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.701180641503443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1916,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-6-astra:5ccf2057056e4d7d",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 1.47583,
        "mean": 1.30343,
        "median": 1.3074612499999998,
        "min": 1.077205,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-05": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 10.42744
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 94.27795884318934,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 63,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:44:38Z",
      "losses": 82,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 80.00375714481252,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1916,
      "rating_method": "sequential_elo",
      "raw_elo": 2135.6057738383734,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 94.27795884318934,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1771
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 2590,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-fable-5-1:76144460966d4171",
      "capped_draws": 1,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 13
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 11.79121,
        "mean": 5.021086745700856,
        "median": 3.933625,
        "min": 2.3764558334148846,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 3,
          "boardgame-list-prices-2026-09-08": 10
        },
        "run_count": 11,
        "token_priced_attempt_count": 13,
        "total": 48.7391179312137
      },
      "codegen_evaluated_cells": 11,
      "conditional_success_score": 91.38911158312541,
      "contributing_entrants": null,
      "distinct_rated_opponents": 69,
      "draws": 70,
      "eligibility_flag": true,
      "entry_count": 11,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.8181818181818182,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "infra_failures_excluded": 5,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:12:04Z",
      "losses": 146,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 79.87031463289088,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2590,
      "rating_method": "sequential_elo",
      "raw_elo": 2118.3599419593484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 2,
      "repaired_rate": 0.18181818181818182,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 91.38911158312541,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 2374
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 720,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-opus-5-5:493e35cd5b85e9e5",
      "capped_draws": 3,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 3.092384,
        "mean": 1.98688675,
        "median": 1.871197,
        "min": 1.357152,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 11
        },
        "run_count": 9,
        "token_priced_attempt_count": 11,
        "total": 17.677191999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 80.9535676866771,
      "contributing_entrants": null,
      "distinct_rated_opponents": 69,
      "draws": 22,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:15Z",
      "losses": 35,
      "max_score": 90.00227559221021,
      "measured_at": null,
      "min_score": 62.15278254588686,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 720,
      "rating_method": "sequential_elo",
      "raw_elo": 1992.9836002881682,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 80.9535676866771,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 663
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 2366,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 4,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 3,
        "max": 2.09943,
        "mean": 1.379653125,
        "median": 1.3205149999999999,
        "min": 0.8875599999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 22.074450000000002
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 76.79197650973506,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 155,
      "eligibility_flag": true,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.8125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:30Z",
      "losses": 326,
      "max_score": 90.34746663281791,
      "measured_at": null,
      "min_score": 59.671054671727674,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 3,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.8125,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2366,
      "rating_method": "sequential_elo",
      "raw_elo": 1947.2184048674094,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 72.90741299156647,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1885
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2618,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 8,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 1.17244375,
        "mean": 0.7965692187500001,
        "median": 0.7419175,
        "min": 0.6308437499999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 6.37255375
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 69.89581987459516,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 195,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:11:13Z",
      "losses": 438,
      "max_score": 89.24673663502878,
      "measured_at": null,
      "min_score": 51.53506842461099,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2617,
      "rating_method": "sequential_elo",
      "raw_elo": 1861.492100901898,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 69.89581987459516,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1984
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1990,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-fable-5:f2454da3451cc4f4",
      "capped_draws": 119,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 2.14955,
        "mean": 1.47056875,
        "median": 1.411685,
        "min": 0.98262,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 11.764549999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 65.1419679067195,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 309,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:12Z",
      "losses": 454,
      "max_score": 85.53702993381843,
      "measured_at": null,
      "min_score": 35.23351331310822,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1983,
      "rating_method": "sequential_elo",
      "raw_elo": 1775.952167016037,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 65.1419679067195,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1220
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 692,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-6-sol:1b97e3eb94454fd6",
      "capped_draws": 3,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.225321,
        "mean": 0.20679475000000003,
        "median": 0.2051385,
        "min": 0.185721,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.6543580000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 61.55693513846125,
      "contributing_entrants": null,
      "distinct_rated_opponents": 68,
      "draws": 64,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:29:41Z",
      "losses": 121,
      "max_score": 82.55615873333252,
      "measured_at": null,
      "min_score": 11.206070516617746,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 692,
      "rating_method": "sequential_elo",
      "raw_elo": 1784.6419125091616,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 61.55693513846125,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 507
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 2382,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 61,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 2.2530275,
        "mean": 1.51903,
        "median": 1.4938600000000002,
        "min": 1.088255,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 12.15224
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 63.56633841927054,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 374,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:53:32Z",
      "losses": 480,
      "max_score": 90.9620272870252,
      "measured_at": null,
      "min_score": 26.396024096701737,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2375,
      "rating_method": "sequential_elo",
      "raw_elo": 1811.0896026439925,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 61.479341753727496,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1521
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1478,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-opus-4-8:10055d865d9a798b",
      "capped_draws": 25,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 1.38945,
        "mean": 0.93123625,
        "median": 0.95991,
        "min": 0.36561,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 7.44989
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 60.64361772447914,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 203,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:11:59Z",
      "losses": 305,
      "max_score": 78.12478117978807,
      "measured_at": null,
      "min_score": 34.48092158803702,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1478,
      "rating_method": "sequential_elo",
      "raw_elo": 1766.38446726309,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 58.652579210624985,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 970
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 6637,
      "canonical_public_row_identity": "publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 186,
      "codegen_cost_usd": {
        "admitted_cell_count": 25,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 31
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 31,
        "run_count": 28,
        "total": 0.0
      },
      "codegen_evaluated_cells": 25,
      "conditional_success_score": 56.87873766350323,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 889,
      "eligibility_flag": true,
      "entry_count": 25,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 22,
      "first_pass_rate": 0.88,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "infra_failures_excluded": 5,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:04:41Z",
      "losses": 1969,
      "max_score": 67.13193639618068,
      "measured_at": null,
      "min_score": 49.54900667277811,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6449,
      "rating_method": "sequential_elo",
      "raw_elo": 1693.7247943349419,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 3,
      "repaired_rate": 0.12,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 56.87873766350323,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 182,
      "wins": 3591
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2048,
      "canonical_public_row_identity": "publication-row.v1:intensive:qwen-qwen3-8-2-4t-a95b:80d9bb5405a8b814",
      "capped_draws": 108,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 10
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.7896974949512139,
        "mean": 0.4317783571024416,
        "median": 0.3306270924500423,
        "min": 0.277380977244658,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 3.454226856819533
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 55.185255291851604,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 528,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:09Z",
      "losses": 499,
      "max_score": 81.83360524090116,
      "measured_at": null,
      "min_score": 19.044287744530894,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2042,
      "rating_method": "sequential_elo",
      "raw_elo": 1727.2085997821755,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 55.185255291851604,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1015
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1397,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-5:5e4063ca612ddcd4",
      "capped_draws": 126,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 4.4173,
        "mean": 2.7356843750000004,
        "median": 2.536595,
        "min": 2.045485,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.885475
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 56.835196114717284,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 306,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:14Z",
      "losses": 248,
      "max_score": 85.64043148326957,
      "measured_at": null,
      "min_score": 10.026592849743277,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1396,
      "rating_method": "sequential_elo",
      "raw_elo": 1749.6293859235354,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 54.969194898876594,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 842
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 670,
      "canonical_public_row_identity": "publication-row.v1:intensive:deepseek-deepseek-v4-1-flash:f710e5b6860059c6",
      "capped_draws": 49,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.031583268,
        "mean": 0.02640173625,
        "median": 0.026524292999999997,
        "min": 0.018252918,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.21121389
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.001670581745614,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 143,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:24:55Z",
      "losses": 119,
      "max_score": 75.19336305189155,
      "measured_at": null,
      "min_score": 26.984183127320136,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 670,
      "rating_method": "sequential_elo",
      "raw_elo": 1693.9878380220237,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 53.001670581745614,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 408
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2218,
      "canonical_public_row_identity": "publication-row.v1:intensive:x-ai-grok-4-6:5c921eacd53762a9",
      "capped_draws": 296,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.28029,
        "mean": 0.23409475,
        "median": 0.240558,
        "min": 0.184404,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 1.872758
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.89362205123531,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 572,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:19:35Z",
      "losses": 614,
      "max_score": 80.29583807622168,
      "measured_at": null,
      "min_score": 32.37146553254912,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2217,
      "rating_method": "sequential_elo",
      "raw_elo": 1663.399470048735,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 52.89362205123531,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1031
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 4581,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 556,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.531673125,
        "mean": 0.47737264687500003,
        "median": 0.48302475,
        "min": 0.3855675,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 7.63796235
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 56.14065082660016,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 843,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-07"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:41:54Z",
      "losses": 1263,
      "max_score": 84.32762532825016,
      "measured_at": null,
      "min_score": 37.63782150579934,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 4575,
      "rating_method": "sequential_elo",
      "raw_elo": 1694.8142290263713,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 52.24476245238841,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 2469
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2174,
      "canonical_public_row_identity": "publication-row.v1:intensive:tencent-hy4-preview:aa03f826bc323244",
      "capped_draws": 376,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.151385561,
        "mean": 0.12117269062500001,
        "median": 0.1216224665,
        "min": 0.099918984,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.9693815250000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.067151128510105,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 606,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:33:41Z",
      "losses": 595,
      "max_score": 77.83883887689821,
      "measured_at": null,
      "min_score": 24.654353233120247,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": 1.0,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2168,
      "rating_method": "sequential_elo",
      "raw_elo": 1648.4158119703436,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 52.067151128510105,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 967
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2092,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-8-flash:7ef3571107626567",
      "capped_draws": 164,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.2764612177973556,
        "mean": 0.14318721034763582,
        "median": 0.1303062996496891,
        "min": 0.10133749410144509,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 1.1454976827810865
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 51.44019386589474,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 341,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:44Z",
      "losses": 655,
      "max_score": 83.10880420461697,
      "measured_at": null,
      "min_score": 21.023257576979688,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2090,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.6772984597571,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 51.44019386589474,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1094
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2198,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-5-flash:27c90777b8ed242d",
      "capped_draws": 115,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.5094276945411561,
        "mean": 0.27056867355814085,
        "median": 0.2333324037943521,
        "min": 0.1875185140307643,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 2.1645493884651272
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 51.327641268902916,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 471,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:53:18Z",
      "losses": 694,
      "max_score": 85.75732154194154,
      "measured_at": null,
      "min_score": 15.041311096948304,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2198,
      "rating_method": "sequential_elo",
      "raw_elo": 1672.51049243344,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 51.327641268902916,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1033
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 3182,
      "canonical_public_row_identity": "publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 106,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.13495079999999998,
        "mean": 0.07455065,
        "median": 0.0607138,
        "min": 0.0448404,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.5964052000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 51.011009449206256,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 589,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:16:11Z",
      "losses": 885,
      "max_score": 79.71896425856343,
      "measured_at": null,
      "min_score": 22.083742425713893,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3181,
      "rating_method": "sequential_elo",
      "raw_elo": 1658.1800255201888,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 51.011009449206256,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1707
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2060,
      "canonical_public_row_identity": "publication-row.v1:intensive:z-ai-glm-5-3-flash:cea57e181d1e302f",
      "capped_draws": 205,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.02871725,
        "mean": 0.014901165624999999,
        "median": 0.013297725,
        "min": 0.0073485,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.11920932499999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.8933219700669,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 434,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:41:47Z",
      "losses": 648,
      "max_score": 73.82177341477453,
      "measured_at": null,
      "min_score": 20.64380726893646,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2060,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.9388407447273,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 50.8933219700669,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 978
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 724,
      "canonical_public_row_identity": "publication-row.v1:intensive:z-ai-glm-5-3-flashx:bccbefa7a7bbd2f2",
      "capped_draws": 59,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.09557687,
        "mean": 0.060370179999999996,
        "median": 0.057823150000000004,
        "min": 0.03447845,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.48296143999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.42811883048915,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 148,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:21:57Z",
      "losses": 197,
      "max_score": 71.74427757233467,
      "measured_at": null,
      "min_score": 24.546741166561926,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 723,
      "rating_method": "sequential_elo",
      "raw_elo": 1641.3311149504323,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 50.42811883048915,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 378
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1740,
      "canonical_public_row_identity": "publication-row.v1:intensive:qwen-qwen3-8-27b:a0a78367379103f7",
      "capped_draws": 126,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.3521656,
        "mean": 0.19569013062499999,
        "median": 0.187188825,
        "min": 0.119031025,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 1.5655210449999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.3101665311099,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 216,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:56:38Z",
      "losses": 620,
      "max_score": 74.90167026913919,
      "measured_at": null,
      "min_score": 32.556710798345804,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": 0.75,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1740,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.0401794830425,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 48.68009515429089,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 904
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2708,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 53,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.50466,
        "mean": 0.35099375,
        "median": 0.321349,
        "min": 0.220732,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 2.8079499999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.793190429889094,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 619,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:11:51Z",
      "losses": 925,
      "max_score": 64.64982345476963,
      "measured_at": null,
      "min_score": 13.894809860305726,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2707,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.327780290315,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 44.793190429889094,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1163
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 696,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-6-luna:6dc463949221612e",
      "capped_draws": 4,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.014153675,
        "mean": 0.0117399875,
        "median": 0.011861425,
        "min": 0.0087063,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.0939199
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.62895753236266,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 98,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:24:49Z",
      "losses": 261,
      "max_score": 76.68636345470857,
      "measured_at": null,
      "min_score": 27.32497239731715,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 696,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.8301081815516,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 43.62895753236266,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 337
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2200,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-terra:7c2a658c6918f6e6",
      "capped_draws": 165,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.45800250000000003,
        "mean": 0.38340421874999997,
        "median": 0.38428625,
        "min": 0.302056875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 3.0672337499999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.857588040641794,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 592,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:32Z",
      "losses": 737,
      "max_score": 76.93585154551911,
      "measured_at": null,
      "min_score": 14.953275323875648,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2194,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.7164673310501,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 41.857588040641794,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 865
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2746,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 269,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.0377622,
        "mean": 0.030833324999999998,
        "median": 0.031411375,
        "min": 0.0247604,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.24666659999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.84697249364046,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 914,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:14:16Z",
      "losses": 760,
      "max_score": 81.2042772769244,
      "measured_at": null,
      "min_score": 11.007260933312008,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2742,
      "rating_method": "sequential_elo",
      "raw_elo": 1573.3676871994946,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 41.84697249364046,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1068
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2198,
      "canonical_public_row_identity": "publication-row.v1:intensive:deepseek-deepseek-v4-pro-0813:980c9c0ee71edcf8",
      "capped_draws": 197,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.28337826924,
        "mean": 0.14657020603499998,
        "median": 0.140081106,
        "min": 0.07036986,
        "recorded_attempt_count": 10,
        "run_count": 8,
        "total": 1.1725616482799999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.51017966504621,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 627,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:12Z",
      "losses": 658,
      "max_score": 71.8729308953561,
      "measured_at": null,
      "min_score": 9.851281775273819,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2198,
      "rating_method": "sequential_elo",
      "raw_elo": 1560.6032297857455,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 41.51017966504621,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 913
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2266,
      "canonical_public_row_identity": "publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 262,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.40721066666666667,
        "mean": 0.3468699583333334,
        "median": 0.3476285,
        "min": 0.237408,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 13,
        "total": 4.659586
      },
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 42.5420873263483,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 620,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.8,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-08"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:17:03Z",
      "losses": 784,
      "max_score": 68.53774121733082,
      "measured_at": null,
      "min_score": 21.383109438871713,
      "model_code_failure_rate": 0.2,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": 0.8,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2266,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.5189111652264,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 40.233822118374256,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 862
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2188,
      "canonical_public_row_identity": "publication-row.v1:intensive:deepseek-deepseek-v4-pro:91e0c8a35047bbc6",
      "capped_draws": 220,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.176790095,
        "mean": 0.114196574281125,
        "median": 0.09418628700000001,
        "min": 0.06074422244,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.9135725942490001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.51200716437151,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 709,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T13:27:12Z",
      "losses": 770,
      "max_score": 75.28091626993594,
      "measured_at": null,
      "min_score": 10.705367299529621,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": 1.0,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2188,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.8265029154468,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.51200716437151,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 709
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1621,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5:7c54c0ad2f51c786",
      "capped_draws": 172,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "max": 0.45464499999999997,
        "mean": 0.28201406249999994,
        "median": 0.2695775,
        "min": 0.17401125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 2.2561124999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.34190463573641,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 538,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:33:18Z",
      "losses": 521,
      "max_score": 70.82103497731079,
      "measured_at": null,
      "min_score": 10.851384971598858,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1620,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.5799551511332,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 38.34190463573641,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 561
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 4898,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 397,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 17
        },
        "cost_is_complete": false,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.512955,
        "mean": 0.43048093750000005,
        "median": 0.4308725,
        "min": 0.32672249999999997,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 8,
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 16,
        "token_priced_attempt_count": 17,
        "total": 6.887695000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 35.45233852196008,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 988,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:16:30Z",
      "losses": 1319,
      "max_score": 59.326053968020524,
      "measured_at": null,
      "min_score": 11.142543596266535,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3488,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.3763603916655,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 35.45233852196008,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1181
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 7960,
      "canonical_public_row_identity": "publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 690,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 32,
          "local_standard_estimate": 8
        },
        "cost_is_complete": false,
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 13,
        "max": 0.1097735,
        "mean": 0.091486,
        "median": 0.08840574999999999,
        "min": 0.0773785,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8,
          "boardgame-list-prices-2026-09-08": 32
        },
        "recorded_attempt_count": 32,
        "run_count": 32,
        "token_priced_attempt_count": 8,
        "total": 2.927552
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 39.689127494925586,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 846,
      "eligibility_flag": true,
      "entry_count": 19,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 19,
      "first_pass_rate": 0.59375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:30Z",
      "losses": 3675,
      "max_score": 52.03780039623947,
      "measured_at": null,
      "min_score": 18.275114149122885,
      "model_code_failure_rate": 0.40625,
      "model_code_failures": 13,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.59375,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 7960,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.4007513152198,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.83954362218033,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 3439
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2086,
      "canonical_public_row_identity": "publication-row.v1:intensive:z-ai-glm-5-2:d977e6638f849d00",
      "capped_draws": 348,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.39278997800000004,
        "mean": 0.1808710912875,
        "median": 0.13158330000000001,
        "min": 0.0448038366,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 1.4469687303
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.185104021864404,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 661,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:03:32Z",
      "losses": 841,
      "max_score": 54.502993109011314,
      "measured_at": null,
      "min_score": 7.705163219117038,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2086,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.2517132222788,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 34.185104021864404,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 584
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2246,
      "canonical_public_row_identity": "publication-row.v1:intensive:bytedance-seed-seed-2-0-code:87a10b251e401fd3",
      "capped_draws": 296,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.075846,
        "mean": 0.050721249999999996,
        "median": 0.04471025,
        "min": 0.0372345,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.40576999999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.015952753786415,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 768,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:21:34Z",
      "losses": 854,
      "max_score": 54.55419811458228,
      "measured_at": null,
      "min_score": 6.506552449736231,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": 1.0,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2242,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.976131255616,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 32.015952753786415,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 620
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1528,
      "canonical_public_row_identity": "publication-row.v1:intensive:tencent-hy3-preview:687d01bcbe0031c5",
      "capped_draws": 115,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.007539277999999999,
        "mean": 0.0032457859375,
        "median": 0.0019568429999999998,
        "min": 0.001266762,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 0.031586439
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 32.87777735942499,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 464,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.5555555555555556,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:55Z",
      "losses": 612,
      "max_score": 61.8142594407856,
      "measured_at": null,
      "min_score": 7.416920025051943,
      "model_code_failure_rate": 0.2222222222222222,
      "model_code_failures": 2,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": 0.7777777777777778,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1526,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.010866053009,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.875665898404755,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 450
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1906,
      "canonical_public_row_identity": "publication-row.v1:intensive:meta-muse-glimmer-30b:b931921706d77dd0",
      "capped_draws": 287,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.02351982,
        "mean": 0.019656965,
        "median": 0.019640945,
        "min": 0.01650772,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.15725572000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.350170089323683,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 778,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:08:41Z",
      "losses": 657,
      "max_score": 45.37253694835636,
      "measured_at": null,
      "min_score": 15.966970879743966,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": 0.875,
      "provider": "Other",
      "provider_key": "other",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1906,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.8301289045526,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 30.320887892682467,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 471
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1830,
      "canonical_public_row_identity": "publication-row.v1:intensive:deepseek-deepseek-v4-flash:bd0b950926bd00a0",
      "capped_draws": 268,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.01423672,
        "mean": 0.0073094338874999994,
        "median": 0.0062260825200000005,
        "min": 0.004397959999999999,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.058475471099999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.445418797781553,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 707,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-05"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:59:44Z",
      "losses": 696,
      "max_score": 79.88316261692358,
      "measured_at": null,
      "min_score": 13.08582389461898,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.875,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1830,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.8547945237258,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 29.44584120542539,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 427
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 5066,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 372,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 50
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0719635,
        "mean": 0.060768406250000004,
        "median": 0.0604727,
        "min": 0.05086675,
        "recorded_attempt_count": 50,
        "run_count": 16,
        "total": 0.9722945000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 29.825390658770534,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 1284,
      "eligibility_flag": true,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.8125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:02:42Z",
      "losses": 2294,
      "max_score": 45.48522862689852,
      "measured_at": null,
      "min_score": 13.016216434051367,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5064,
      "rating_method": "sequential_elo",
      "raw_elo": 1376.5008103656928,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 28.84616969998549,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1486
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1738,
      "canonical_public_row_identity": "publication-row.v1:intensive:openai-gpt-oss-120b:e79c900fda7b779f",
      "capped_draws": 215,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.015120192000000001,
        "mean": 0.0074424702499999995,
        "median": 0.006876,
        "min": 0.00134592,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.05953976200000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 27.683808602948602,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 640,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:12Z",
      "losses": 694,
      "max_score": 54.825621514346786,
      "measured_at": null,
      "min_score": 13.144887580099901,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1737,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.8254108981453,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 26.774899616201456,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 403
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 2361,
      "canonical_public_row_identity": "publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 292,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.06806129999999999,
        "mean": 0.037113121874999995,
        "median": 0.0310111,
        "min": 0.0230335,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 10,
        "total": 0.3876148499999999
      },
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 27.23956902599473,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 794,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.6,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:31:53Z",
      "losses": 1004,
      "max_score": 51.611716687770866,
      "measured_at": null,
      "min_score": 10.433188741667081,
      "model_code_failure_rate": 0.2,
      "model_code_failures": 2,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": 0.8,
      "provider": "Other",
      "provider_key": "other",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2361,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.115355812149,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 2,
      "repaired_rate": 0.2,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.761593839197328,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 563
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1908,
      "canonical_public_row_identity": "publication-row.v1:intensive:mistralai-mistral-medium-3-5:eaf038eae77e915a",
      "capped_draws": 199,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 13
        },
        "cost_is_complete": true,
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.27741402547937455,
        "mean": 0.17469283299791016,
        "median": 0.15577176465417142,
        "min": 0.1042008119864669,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 13
        },
        "run_count": 8,
        "token_priced_attempt_count": 13,
        "total": 1.3975426639832813
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 26.017320074855167,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 719,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:28:48Z",
      "losses": 816,
      "max_score": 56.99034820792066,
      "measured_at": null,
      "min_score": 13.027941933509863,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": 0.875,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1902,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.1724393636034,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.16312488927676,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 367
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1111,
      "canonical_public_row_identity": "publication-row.v1:intensive:stepfun-step-3-7-flash:4b833cb2e8aaef2e",
      "capped_draws": 212,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.11219570000000001,
        "mean": 0.0607572625,
        "median": 0.060057275,
        "min": 0.02174195,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.48605810000000005
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.20832575549643,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 220,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:08:15Z",
      "losses": 609,
      "max_score": 42.50033505424671,
      "measured_at": null,
      "min_score": 11.850477367246295,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": 0.625,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1111,
      "rating_method": "sequential_elo",
      "raw_elo": 1242.901118933249,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 25.08114244133497,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 282
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 3648,
      "canonical_public_row_identity": "publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 410,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.302804525,
        "mean": 0.259828169375,
        "median": 0.2529231275,
        "min": 0.22308452,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 4.15725071
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.48988573112342,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 1167,
      "eligibility_flag": true,
      "entry_count": 9,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:44:38Z",
      "losses": 1726,
      "max_score": 53.98273918474334,
      "measured_at": null,
      "min_score": 8.759478344679279,
      "model_code_failure_rate": 0.4375,
      "model_code_failures": 7,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.5625,
      "provider": "Other",
      "provider_key": "other",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3646,
      "rating_method": "sequential_elo",
      "raw_elo": 1344.5096166882668,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 23.806939390284235,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 753
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:intensive:xiaomi-mimo-v2-5:d38137ce389958c3",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0597184625,
        "mean": 0.02467013555,
        "median": 0.0239011175,
        "min": 0.0040410944,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.1973610844
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 25.491686551767373,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 593,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05",
        "GB2-07"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:03:41Z",
      "losses": 310,
      "max_score": 48.979799568566214,
      "measured_at": null,
      "min_score": 13.398467888140017,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.625,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1024,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.9768926712727,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 22.665670661087013,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 121
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 1867,
      "canonical_public_row_identity": "publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:abf00b9c47e30ff5",
      "capped_draws": 362,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.0456916,
        "mean": 0.031545040625,
        "median": 0.035551075,
        "min": 0.01864685,
        "recorded_attempt_count": 35,
        "run_count": 16,
        "total": 0.5047206500000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 24.21543621287482,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 870,
      "eligibility_flag": true,
      "entry_count": 9,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:30Z",
      "losses": 689,
      "max_score": 37.7955878292642,
      "measured_at": null,
      "min_score": 8.523437707990063,
      "model_code_failure_rate": 0.4375,
      "model_code_failures": 7,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": 0.5625,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1867,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.5216328058705,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 20.971182924071233,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 308
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1119,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-1-flash-lite:3af992128398834e",
      "capped_draws": 157,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0422995,
        "mean": 0.027492531250000004,
        "median": 0.025548,
        "min": 0.0204145,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.21994025
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 21.107450358093807,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 310,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:27:10Z",
      "losses": 614,
      "max_score": 29.827400148127907,
      "measured_at": null,
      "min_score": 14.9868688465287,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": 0.625,
      "provider": "Google",
      "provider_key": "google",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1119,
      "rating_method": "sequential_elo",
      "raw_elo": 1195.8366238188325,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 18.767472185108453,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 195
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1624,
      "canonical_public_row_identity": "publication-row.v1:intensive:inception-mercury-2-5-preview:e936b6bbd630c36b",
      "capped_draws": 263,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0021869100000000002,
        "mean": 0.0013222775000000001,
        "median": 0.001054655,
        "min": 0.00083106,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.010578220000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 19.41544742908869,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 716,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T15:54:30Z",
      "losses": 750,
      "max_score": 29.334163810673346,
      "measured_at": null,
      "min_score": 14.494975929834537,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1624,
      "rating_method": "sequential_elo",
      "raw_elo": 1249.700662697952,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 18.068109719151302,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 158
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1732,
      "canonical_public_row_identity": "publication-row.v1:intensive:z-ai-glm-5-3:e8ce4aed95c7494d",
      "capped_draws": 20,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.5256212,
        "mean": 0.38805244562499996,
        "median": 0.41839404999999996,
        "min": 0.063446985,
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 3.104419565
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 79.76036427478273,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 193,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-04"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:20:12Z",
      "losses": 155,
      "max_score": 97.58127501121015,
      "measured_at": null,
      "min_score": 39.53484749867363,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1726,
      "rating_method": "sequential_elo",
      "raw_elo": 2029.3949496925354,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 79.76036427478273,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1378
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-row.v1:intensive:x-ai-grok-4-7:bcff48978031cd50",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 3,
        "cell_count": 5,
        "cost_basis_counts": {
          "provider_reported": 5
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.5756864,
        "mean": 0.31644575999999996,
        "median": 0.4788,
        "min": 0.0,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 3
        },
        "recorded_attempt_count": 5,
        "run_count": 5,
        "total": 1.5822288
      },
      "codegen_evaluated_cells": 3,
      "conditional_success_score": 61.511708255394375,
      "contributing_entrants": null,
      "distinct_rated_opponents": 59,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": 3,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 3,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:05:46Z",
      "losses": 58,
      "max_score": 65.39633278537028,
      "measured_at": null,
      "min_score": 58.418768085533685,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1771.826073378752,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 61.511708255394375,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 211
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 1490,
      "canonical_public_row_identity": "publication-row.v1:intensive:meta-muse-spark-1-3:a15c2acfd980b456",
      "capped_draws": 3,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 7
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.273243,
        "mean": 0.18666160714285715,
        "median": 0.20966,
        "min": 0.0,
        "recorded_attempt_count": 7,
        "run_count": 7,
        "total": 1.30663125
      },
      "codegen_evaluated_cells": 6,
      "conditional_success_score": 54.58231057179747,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 300,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-05"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:20:11Z",
      "losses": 386,
      "max_score": 77.02031061725003,
      "measured_at": null,
      "min_score": 16.539487456961396,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1489,
      "rating_method": "sequential_elo",
      "raw_elo": 1715.4859427661202,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 54.58231057179747,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 803
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 574,
      "canonical_public_row_identity": "publication-row.v1:intensive:qwen-qwen3-8-max-0902:b1160daf60583f67",
      "capped_draws": 71,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "max": 0.606316,
        "mean": 0.33312575,
        "median": 0.357252,
        "min": 0.0,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-09-08": 8
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 2.665006
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 54.36706229997475,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 148,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.8571428571428571,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-07"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T16:15:55Z",
      "losses": 74,
      "max_score": 76.38881018245638,
      "measured_at": null,
      "min_score": 31.282600931503342,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 574,
      "rating_method": "sequential_elo",
      "raw_elo": 1708.5008524462214,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 1,
      "repaired_rate": 0.14285714285714285,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 54.36706229997475,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 352
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 772,
      "canonical_public_row_identity": "publication-row.v1:intensive:meta-muse-spark-1-2:8ed12b9970d2209b",
      "capped_draws": 52,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 2,
        "cost_basis_counts": {
          "provider_reported": 2
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "max": 0.143734,
        "mean": 0.123945875,
        "median": 0.123945875,
        "min": 0.10415775,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 2
        },
        "recorded_attempt_count": 2,
        "run_count": 2,
        "total": 0.24789175
      },
      "codegen_evaluated_cells": 2,
      "conditional_success_score": 46.151515774593946,
      "contributing_entrants": null,
      "distinct_rated_opponents": 62,
      "draws": 96,
      "eligibility_flag": false,
      "entry_count": 2,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 2,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T12:26:40Z",
      "losses": 306,
      "max_score": 52.012365091494885,
      "measured_at": null,
      "min_score": 40.290666457693014,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 772,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.990422317601,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 46.151515774593946,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 370
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1986,
      "canonical_public_row_identity": "publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 53,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "cost_is_complete": false,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.6279041999999999,
        "mean": 0.526117125,
        "median": 0.5491332,
        "min": 0.330054,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 15
        },
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 4.208936999999999
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 43.19539960693221,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 637,
      "eligibility_flag": false,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-05",
        "GB2-06"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.14285714285714285,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T14:07:06Z",
      "losses": 555,
      "max_score": 58.56757191941488,
      "measured_at": null,
      "min_score": 10.856245227633352,
      "model_code_failure_rate": 0.2857142857142857,
      "model_code_failures": 2,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 0.7142857142857143,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1974,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.606340835216,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 4,
      "repaired_rate": 0.5714285714285714,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 39.710512051870296,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 782
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-row.v1:intensive:ibm-granite-granite-4-2-8b:29cc10e0f4501f9b",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "cost_is_complete": true,
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.010999479999999999,
        "mean": 0.007405580000000001,
        "median": 0.00734207,
        "min": 0.0037107299999999998,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.05924464000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 20.205129732851056,
      "contributing_entrants": null,
      "distinct_rated_opponents": 50,
      "draws": 178,
      "eligibility_flag": false,
      "entry_count": 1,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-09-25T07:53:01Z",
      "losses": 68,
      "max_score": 20.205129732851056,
      "measured_at": null,
      "min_score": 20.205129732851056,
      "model_code_failure_rate": 0.875,
      "model_code_failures": 7,
      "model_display_name": "Granite 4.2 8B",
      "model_slug": "ibm-granite-granite-4-2-8b",
      "plugin_success_rate": 0.125,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.7415020745286,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Full",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Full",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Full",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "track",
      "score": 12.014042018929752,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 218,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-6-astra:5ccf2057056e4d7d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 2196.543718849944,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 93.77364643873946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 211
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 310,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-09-25T05:16:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 310,
      "rating_method": "sequential_elo",
      "raw_elo": 2152.9795477867438,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 90.9620272870252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 290
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 218,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:google-gemini-3-5-flash:27c90777b8ed242d",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-25T15:53:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 218,
      "rating_method": "sequential_elo",
      "raw_elo": 2084.7316454501633,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.75732154194154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 184
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-fable-5-1:76144460966d4171",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T07:14:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 2002.0226474993385,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 79.87031463289088,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 203
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:z-ai-glm-5-3:e8ce4aed95c7494d",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1945.0536760331718,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.80228272363448,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 382,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 75,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T14:16:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 382,
      "rating_method": "sequential_elo",
      "raw_elo": 1918.6768759763554,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.32458663155238,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 271
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-fable-5:f2454da3451cc4f4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T06:19:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1918.3659092889625,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 73.84725078211831,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 186
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-5:5e4063ca612ddcd4",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T14:02:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1872.6133126290345,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.24122372942317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:meta-muse-spark-1-3:a15c2acfd980b456",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-09-25T06:19:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1813.8305646022727,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.39429069545992,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-4-8:10055d865d9a798b",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T13:07:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1797.8711663723197,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.07517251306582,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 127
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-6-terra:7c2a658c6918f6e6",
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 45,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T13:19:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1794.308216479141,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.05600675030205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T02:40:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.2463407968028,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 64.97146846724627,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 207
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T14:08:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1763.003514868158,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.01830422379207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 232
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-5-5:493e35cd5b85e9e5",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1773.4684559371246,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.15278254588686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 132,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1725.375924521653,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.671054671727674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 213
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 523,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 127,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 181,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 104,
      "max_score": null,
      "measured_at": "2026-09-25T05:05:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 357,
      "rating_method": "sequential_elo",
      "raw_elo": 1710.178254810776,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.326053968020524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 197
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 398,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 127,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 392,
      "rating_method": "sequential_elo",
      "raw_elo": 1698.6355858236166,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.56757191941488,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 223
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:x-ai-grok-4-7:bcff48978031cd50",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T12:50:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1720.288436114733,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.418768085533685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:qwen-qwen3-8-27b:a0a78367379103f7",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-09-25T02:27:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1701.67334656394,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.407241304881026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 157
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:tencent-hy3-preview:687d01bcbe0031c5",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-25T04:53:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1689.2694783053653,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.3097596033617,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 304,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:z-ai-glm-5-3-flash:cea57e181d1e302f",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 304,
      "rating_method": "sequential_elo",
      "raw_elo": 1682.8213386192058,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.23829261695304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 201
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 406,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T13:19:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 406,
      "rating_method": "sequential_elo",
      "raw_elo": 1651.1585365823491,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.18882050646197,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 225
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 380,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:meta-muse-spark-1-2:8ed12b9970d2209b",
      "capped_draws": 36,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 130,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 146,
      "max_score": null,
      "measured_at": "2026-09-25T05:16:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 380,
      "rating_method": "sequential_elo",
      "raw_elo": 1607.5185452601124,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.012365091494885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 198
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:qwen-qwen3-8-max-0902:b1160daf60583f67",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1617.3499846972302,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.78300254547936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:deepseek-deepseek-v4-1-flash:f710e5b6860059c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T12:45:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.2608269926718,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.58183366585325,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 794,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 349,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 359,
      "max_score": null,
      "measured_at": "2026-09-25T16:04:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 794,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.345424331282,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.54900667277811,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 384
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:tencent-hy4-preview:aa03f826bc323244",
      "capped_draws": 162,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 136,
      "draws": 162,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1569.5488822308891,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.15370367716753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 753,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 230,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 252,
      "draws": 230,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 257,
      "max_score": null,
      "measured_at": "2026-09-25T13:19:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 750,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.8876848351229,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.08301890379797,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 263
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:z-ai-glm-5-2:d977e6638f849d00",
      "capped_draws": 112,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 112,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 91,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.3621536320004,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.13787652878352,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:google-gemini-3-8-flash:7ef3571107626567",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 134,
      "max_score": null,
      "measured_at": "2026-09-25T13:19:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.558062708041,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.63626796266691,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:qwen-qwen3-8-2-4t-a95b:80d9bb5405a8b814",
      "capped_draws": 104,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 133,
      "draws": 104,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 102,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.1200824179782,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.61493415632901,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:x-ai-grok-4-6:5c921eacd53762a9",
      "capped_draws": 168,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 139,
      "draws": 168,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 316,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.1969563117673,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.46326454223426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 1078,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 111,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 346,
      "draws": 111,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 434,
      "max_score": null,
      "measured_at": "2026-09-25T14:13:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 1078,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.3202629319196,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 44.356829595027115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 533
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:deepseek-deepseek-v4-pro-0813:980c9c0ee71edcf8",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-09-25T12:56:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.8060324709397,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.654809510966054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 184,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.7279758888242,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.24576283638427,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:bytedance-seed-seed-2-0-code:87a10b251e401fd3",
      "capped_draws": 133,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 133,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T14:13:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.1846187113122,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.31602941916818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:z-ai-glm-5-3-flashx:bccbefa7a7bbd2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.1229581263374,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.075433997538745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5:7c54c0ad2f51c786",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 83,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T13:25:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.2005538627475,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.22556272805624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 224,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 117,
      "max_score": null,
      "measured_at": "2026-09-25T01:38:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 224,
      "rating_method": "sequential_elo",
      "raw_elo": 1343.3023635597492,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.62683857968774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-6-luna:6dc463949221612e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.9508017642634,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.577483197926895,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:meta-muse-glimmer-30b:b931921706d77dd0",
      "capped_draws": 75,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T06:19:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.8405122937986,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.03694030645199,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:inception-mercury-2-5-preview:e936b6bbd630c36b",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 81,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 147,
      "max_score": null,
      "measured_at": "2026-09-25T13:58:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1294.656689306476,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.334163810673346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 81,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T13:19:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1282.677883060552,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.35256079649359,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:abf00b9c47e30ff5",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 87,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 118,
      "max_score": null,
      "measured_at": "2026-09-23T04:29:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1247.2566040724391,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.687756439022323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 358,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 137,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 137,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 205,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 358,
      "rating_method": "sequential_elo",
      "raw_elo": 1234.1136208078292,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.196890039181877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:xiaomi-mimo-v2-5:d38137ce389958c3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 85,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-09-25T16:03:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1234.61584720606,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.46942855390865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.385165364704298,
      "unilateral_faults": null,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:deepseek-deepseek-v4-pro:91e0c8a35047bbc6",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 163,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1197.9967349311883,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.258235865851287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:deepseek-deepseek-v4-flash:bd0b950926bd00a0",
      "capped_draws": 62,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 152,
      "max_score": null,
      "measured_at": "2026-09-25T07:56:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1150.6627242367563,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.807057281000937,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:stepfun-step-3-7-flash:4b833cb2e8aaef2e",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 139,
      "max_score": null,
      "measured_at": "2026-09-25T05:34:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1057.2574789116686,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.850477367246295,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-6-sol:1b97e3eb94454fd6",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-25T12:15:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1065.329091592359,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.206070516617746,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-6-astra:5ccf2057056e4d7d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 2063.9275630488323,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 219
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-fable-5-1:76144460966d4171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 2017.5102993445785,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 93.36562317213091,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 204
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-opus-5-5:493e35cd5b85e9e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1956.270414304034,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 82.7940575934645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 136,
      "draws": 88,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1818.8505392710506,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.01945157758348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 245
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:tencent-hy4-preview:aa03f826bc323244",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-09-25T15:33:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.1900957382898,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.51065884687536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 170
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:x-ai-grok-4-6:5c921eacd53762a9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 227,
      "rating_method": "sequential_elo",
      "raw_elo": 1788.033141954644,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.09063610309277,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-fable-5:f2454da3451cc4f4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1774.561902563198,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.21782579520304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-opus-4-8:10055d865d9a798b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1749.994117056542,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.64032909915444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 332,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 108,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T05:15:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 332,
      "rating_method": "sequential_elo",
      "raw_elo": 1715.609120411484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.53506842461099,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 197
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 496,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 194,
      "draws": 175,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 496,
      "rating_method": "sequential_elo",
      "raw_elo": 1717.3031610635599,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.28648284773156,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 278
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:google-gemini-3-8-flash:7ef3571107626567",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 97,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.5162560866765,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.106142336092056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-6-sol:1b97e3eb94454fd6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1650.7341735576565,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.644601832444756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:z-ai-glm-5-3-flash:cea57e181d1e302f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 121,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.8527377787163,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.574682510188765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:z-ai-glm-5-3:e8ce4aed95c7494d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 133,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.350599063675,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.53484749867363,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-6-luna:6dc463949221612e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.9847755272187,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.736737545406314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:z-ai-glm-5-3-flashx:bccbefa7a7bbd2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.6787937426257,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.13947827988383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 352,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 182,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.403733556461,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.977282075387954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:z-ai-glm-5-2:d977e6638f849d00",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 122,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1588.4441487763484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.03910046349824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:qwen-qwen3-8-max-0902:b1160daf60583f67",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.9174124025324,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.282600931503342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5-6-terra:7c2a658c6918f6e6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 140,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T05:31:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.9017626387488,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.58419652878032,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:google-gemini-3-5-flash:27c90777b8ed242d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 145,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.2698824483814,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.850032552789482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:deepseek-deepseek-v4-1-flash:f710e5b6860059c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.7555095702419,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.984183127320136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 261,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 198,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T05:15:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 261,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.294948942284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.383109438871713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:qwen-qwen3-8-2-4t-a95b:80d9bb5405a8b814",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 159,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.068223724876,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.044287744530894,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:meta-muse-spark-1-3:a15c2acfd980b456",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 191,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.2377075518823,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.539487456961396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:meta-muse-glimmer-30b:b931921706d77dd0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 232,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.5747369427895,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.966970879743966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 270,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:inception-mercury-2-5-preview:e936b6bbd630c36b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 245,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 270,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.7005581154203,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.879637514716912,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:deepseek-deepseek-v4-flash:bd0b950926bd00a0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 180,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T03:35:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.0772478703082,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.424491371108513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 296,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 263,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.6194687642037,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.894809860305726,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:mistralai-mistral-medium-3-5:eaf038eae77e915a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 245,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.7289649498068,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.661100526328765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:xiaomi-mimo-v2-5:d38137ce389958c3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "draws": 157,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.166005128762,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.398467888140017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.132002100700243,
      "unilateral_faults": null,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:openai-gpt-oss-120b:e79c900fda7b779f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 196,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.8502480309085,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.144887580099901,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 352,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 271,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.4601523846961,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.016216434051367,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 296,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 256,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.7146270238864,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.781594766493846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 578,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 194,
      "draws": 301,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-25T14:09:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.5767306944488,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.142543596266535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 125,
      "draws": 302,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.6557046760618,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.856245227633352,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 200,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5:7c54c0ad2f51c786",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 79,
      "draws": 159,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.0118488111527,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.851384971598858,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:deepseek-deepseek-v4-pro:91e0c8a35047bbc6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.5205440495274,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.705367299529621,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 258,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.6576556254138,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.433188741667081,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 274,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:deepseek-deepseek-v4-pro-0813:980c9c0ee71edcf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 225,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.8172875640382,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 9.851281775273819,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 384,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 337,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-23T22:15:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 382,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.3826257930446,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.759478344679279,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 388,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:abf00b9c47e30ff5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 149,
      "draws": 336,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 388,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.916593140943,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.523437707990063,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:bytedance-seed-seed-2-0-code:87a10b251e401fd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 208,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.1822389925464,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 8.075838704215268,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 202,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:tencent-hy3-preview:687d01bcbe0031c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 165,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 200,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.6240175501182,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.416920025051943,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 2,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-6-astra:5ccf2057056e4d7d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-09-25T07:40:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 2163.5190039337767,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 227
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 448,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-fable-5-1:76144460966d4171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 203,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 448,
      "rating_method": "sequential_elo",
      "raw_elo": 2059.1206107382654,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 90.12297537243145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 409
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 111,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T13:18:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 2057.4923993127013,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 89.1770885247866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.48567977499789805,
      "unilateral_faults": 0,
      "wins": 240
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:z-ai-glm-5-3:e8ce4aed95c7494d",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 2002.6753583822758,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 84.96955467101989,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-opus-5-5:493e35cd5b85e9e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1944.5287804487727,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.19523136118757,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-6-sol:1b97e3eb94454fd6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1899.422086219661,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.72412581235643,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:qwen-qwen3-8-2-4t-a95b:80d9bb5405a8b814",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 102,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1853.5765514492996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.85712897377837,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-fable-5:f2454da3451cc4f4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-24T21:02:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1832.5446903752695,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.91099828064931,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 144
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:z-ai-glm-5-3-flash:cea57e181d1e302f",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1769.4036597862491,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.99601875550448,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 310,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 309,
      "rating_method": "sequential_elo",
      "raw_elo": 1755.6663153829472,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.971421270163184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 245
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-8-flash:7ef3571107626567",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 231,
      "rating_method": "sequential_elo",
      "raw_elo": 1734.0510593713882,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.606732398356996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 144
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 1255,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 5,
      "distinct_rated_opponents": 503,
      "draws": 209,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 252,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 1067,
      "rating_method": "sequential_elo",
      "raw_elo": 1714.6275748238265,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.64563528194297,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 182,
      "wins": 606
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-5-flash:27c90777b8ed242d",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1691.0453258781433,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.60089993691927,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:z-ai-glm-5-3-flashx:bccbefa7a7bbd2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T14:10:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1681.9417056415027,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.44037344594306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-09-25T14:34:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1640.6919382738752,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.2458282828391,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 196
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:meta-muse-spark-1-3:a15c2acfd980b456",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T05:09:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 231,
      "rating_method": "sequential_elo",
      "raw_elo": 1635.343723849433,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.32890841701454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:tencent-hy4-preview:aa03f826bc323244",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-09-25T13:18:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.8637733818819,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.95177486372414,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:qwen-qwen3-8-max-0902:b1160daf60583f67",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-09-25T14:01:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.8364247304644,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.941446429504964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:deepseek-deepseek-v4-pro-0813:980c9c0ee71edcf8",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-09-25T12:11:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.6780053004868,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.221073631451,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 132
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 247,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 97,
      "max_score": null,
      "measured_at": "2026-09-25T12:01:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 247,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.2689260067089,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.73709363383094,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 316,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 106,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T07:53:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 315,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.8305710643456,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.028376243947854,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 392,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:meta-muse-spark-1-2:8ed12b9970d2209b",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 160,
      "max_score": null,
      "measured_at": "2026-09-25T12:26:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 392,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.4622993750897,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.290666457693014,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:deepseek-deepseek-v4-1-flash:f710e5b6860059c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-25T14:29:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.8733133898322,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 39.21094528138139,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 184,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 116,
      "max_score": null,
      "measured_at": "2026-09-25T13:00:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 390,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.6866651776409,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.017147044794186,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:x-ai-grok-4-6:5c921eacd53762a9",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 81,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.1119937212918,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.55815458856067,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 121
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 157,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-5:5e4063ca612ddcd4",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.6170637154105,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.09937739195498,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 750,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 256,
      "draws": 167,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 296,
      "max_score": null,
      "measured_at": "2026-09-25T15:19:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 750,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.2227097154012,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.923231532018065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 287
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 324,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:deepseek-deepseek-v4-pro:91e0c8a35047bbc6",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 135,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 104,
      "max_score": null,
      "measured_at": "2026-09-25T07:24:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.3723474587694,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.70168001380781,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 85
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 430,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 147,
      "draws": 157,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 151,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 430,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.299023042923,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.713474611999153,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:meta-muse-glimmer-30b:b931921706d77dd0",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 111,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T05:13:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.0818669469777,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.333463916130018,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:z-ai-glm-5-2:d977e6638f849d00",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T16:03:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.2081191859868,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.24083392559777,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:openai-gpt-oss-120b:e79c900fda7b779f",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 94,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T14:10:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 237,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.1661562967663,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.416960415799508,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 226,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-6-terra:7c2a658c6918f6e6",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 97,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T13:01:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.6974052765618,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.152984788095484,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:mistralai-mistral-medium-3-5:eaf038eae77e915a",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 91,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.3861199840924,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.792321610997423,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:bytedance-seed-seed-2-0-code:87a10b251e401fd3",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 109,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-09-25T13:13:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.4737461688474,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.37320291516669,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 286,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 76,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T05:38:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.7927382313237,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.343796015821606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-6-luna:6dc463949221612e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-09-25T14:22:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.7374212036264,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.32497239731715,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 386,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 139,
      "draws": 173,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 142,
      "max_score": null,
      "measured_at": "2026-09-25T12:11:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 383,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.944398778814,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.96684174359192,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 393,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 137,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 142,
      "max_score": null,
      "measured_at": "2026-09-25T12:54:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 389,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.71380781756,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.396024096701737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 354,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 27,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 150,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 115,
      "max_score": null,
      "measured_at": "2026-09-25T12:55:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 353,
      "rating_method": "sequential_elo",
      "raw_elo": 1361.9795528555346,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.104629327422128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 372,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 127,
      "draws": 97,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 150,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.9441679487495,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.4009168781914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:deepseek-deepseek-v4-flash:bd0b950926bd00a0",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 103,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1332.266627525364,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.86788153475712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 143,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5:7c54c0ad2f51c786",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1339.318229141879,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.82884738650803,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:ibm-granite-granite-4-2-8b:29cc10e0f4501f9b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 178,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-09-25T07:53:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Granite 4.2 8B",
      "model_slug": "ibm-granite-granite-4-2-8b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1313.7415020745286,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Full",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "ibm-granite/granite-4.2-8b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Full",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Full",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.205129732851056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 394,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 124,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 180,
      "max_score": null,
      "measured_at": "2026-09-25T05:53:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 394,
      "rating_method": "sequential_elo",
      "raw_elo": 1288.1863481775406,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.275114149122885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-6-astra:5ccf2057056e4d7d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-18T18:46:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1971.8262474267835,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 97.3475278073704,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 208
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-opus-5-5:493e35cd5b85e9e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1938.5493344877893,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 90.00227559221021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-fable-5:f2454da3451cc4f4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 90,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 235,
      "rating_method": "sequential_elo",
      "raw_elo": 1893.5270627446387,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.53702993381843,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 470,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-fable-5-1:76144460966d4171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 203,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 470,
      "rating_method": "sequential_elo",
      "raw_elo": 1881.2969682397602,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 83.69072312275135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 391
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1824.75684458976,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.61817300254005,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 234
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 400,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 142,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-09-25T12:27:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 400,
      "rating_method": "sequential_elo",
      "raw_elo": 1822.8530033140737,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.54068913938104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 292
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:z-ai-glm-5-3-flash:cea57e181d1e302f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1766.1518146573342,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.33514913196505,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 156
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:qwen-qwen3-8-max-0902:b1160daf60583f67",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1764.5604542591154,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.02862383954646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-6-sol:1b97e3eb94454fd6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-09-25T03:35:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1755.6273778628556,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.103159443224804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:qwen-qwen3-8-27b:a0a78367379103f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1699.05144103761,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.3162952972934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:z-ai-glm-5-3-flashx:bccbefa7a7bbd2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 85,
      "rating_method": "sequential_elo",
      "raw_elo": 1715.2006324965307,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.03914060818941,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 10.16638660171921,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:deepseek-deepseek-v4-1-flash:f710e5b6860059c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1712.5593249631836,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.52382996903797,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 362,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 109,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 362,
      "rating_method": "sequential_elo",
      "raw_elo": 1682.9100428921965,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.50674408464692,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 702,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 313,
      "draws": 235,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 91,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 702,
      "rating_method": "sequential_elo",
      "raw_elo": 1686.5855614897616,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.29144742349905,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 376
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 241,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 102,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 241,
      "rating_method": "sequential_elo",
      "raw_elo": 1615.0006829372037,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.54396182565621,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 720,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 238,
      "draws": 230,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 183,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 717,
      "rating_method": "sequential_elo",
      "raw_elo": 1594.8571569382302,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.20004663167366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 304
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 315,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 163,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T07:49:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.9896839264163,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.38810520024291,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-6-luna:6dc463949221612e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-09-25T05:36:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1588.7967516245444,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.761198585719725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:x-ai-grok-4-6:5c921eacd53762a9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 137,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 82,
      "max_score": null,
      "measured_at": "2026-09-25T06:00:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.2109146893276,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.57744830171936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 204,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-opus-4-8:10055d865d9a798b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 86,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-09-25T06:53:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 204,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.1828199120182,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 34.48092158803702,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:z-ai-glm-5-2:d977e6638f849d00",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 88,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-09-25T15:34:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.1922997177962,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.06169697877685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:tencent-hy4-preview:aa03f826bc323244",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 115,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.201890822483,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.959581269225342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 340,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 181,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 340,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.6188990359437,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.758173635715277,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:meta-muse-glimmer-30b:b931921706d77dd0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 169,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-09-25T05:13:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.4979397865784,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.427715764746406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 362,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 155,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 362,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.1095908237608,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.083742425713893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:deepseek-deepseek-v4-pro:91e0c8a35047bbc6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 142,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-09-25T13:27:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.6180884228831,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.2316997815558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-8-flash:7ef3571107626567",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 107,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 233,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.2382047303836,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.023257576979688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 418,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 130,
      "draws": 264,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-09-25T05:46:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 418,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.5491498281401,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.86000846438864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:qwen-qwen3-8-2-4t-a95b:80d9bb5405a8b814",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 136,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T15:55:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.8734672756627,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.985371794844777,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5:7c54c0ad2f51c786",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 85,
      "draws": 149,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-09-23T03:30:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.7282264128946,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.492108948060444,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:xiaomi-mimo-v2-5:d38137ce389958c3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 27,
      "draws": 159,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.0490320389179,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.91085216964937,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.834993123162105,
      "unilateral_faults": null,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 295,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 171,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 295,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.3415254636288,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.740585261422419,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-1-flash-lite:3af992128398834e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 153,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.365696951213,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.135889350399117,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-5-flash:27c90777b8ed242d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 137,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-09-25T06:00:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.4930188095987,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.041311096948304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 713,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 227,
      "draws": 460,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 169,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 711,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.0892976785772,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.956475308723242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-6-terra:7c2a658c6918f6e6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 175,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-09-25T05:45:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.0809876221997,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.953275323875648,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:openai-gpt-oss-120b:e79c900fda7b779f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 158,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.6481745285778,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.904812286411738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 268,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:inception-mercury-2-5-preview:e936b6bbd630c36b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 205,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 268,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.2283406234515,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.494975929834537,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 322,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:deepseek-deepseek-v4-pro-0813:980c9c0ee71edcf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 167,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-09-23T05:49:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 322,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.2924084625038,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.07171218097534,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 212,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:abf00b9c47e30ff5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 156,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T14:19:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 212,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.3822018342894,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.307756675211982,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 296,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:deepseek-deepseek-v4-flash:bd0b950926bd00a0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 129,
      "draws": 162,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.714716134723,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.08582389461898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:mistralai-mistral-medium-3-5:eaf038eae77e915a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 184,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T05:08:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.2686820058884,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 13.027941933509863,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 659,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 217,
      "draws": 245,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 138,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 437,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.22162299903,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 12.573294252110319,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:tencent-hy3-preview:687d01bcbe0031c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 93,
      "draws": 184,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-23T17:36:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.9968696972862,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.384109348575187,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 185,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 82,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1396.7896230760327,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 11.007260933312008,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-5:5e4063ca612ddcd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 129,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.516912386562,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 10.026592849743277,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 232,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:bytedance-seed-seed-2-0-code:87a10b251e401fd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 94,
      "draws": 164,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.2351489145487,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 6.506552449736231,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-6-astra:5ccf2057056e4d7d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 2305.8243911075265,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 99.99999999999999,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 236
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:z-ai-glm-5-3:e8ce4aed95c7494d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 2194.1105298945445,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 92.95824569345824,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 218
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-fable-5-1:76144460966d4171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 97,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 2169.720549071415,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 91.37112263611337,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 208
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 138,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-09-25T12:22:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 2156.975351125996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 90.34746663281791,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 316
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-opus-5-5:493e35cd5b85e9e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-09-25T13:22:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 2069.1372139350938,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 83.89765057926846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 704,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 236,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 704,
      "rating_method": "sequential_elo",
      "raw_elo": 2025.4729516225789,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 82.64092472785092,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 594
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 324,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 118,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1999.13038791591,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 80.92593525080028,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 290
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:x-ai-grok-4-6:5c921eacd53762a9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-09-25T12:48:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 1993.0294584176775,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 80.29583807622168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:qwen-qwen3-8-max-0902:b1160daf60583f67",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1951.080125087102,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.38881018245638,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-6-sol:1b97e3eb94454fd6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-09-25T05:23:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1931.5983388188122,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.30573119224167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:z-ai-glm-5-3-flash:cea57e181d1e302f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-09-25T15:41:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1889.6822090150788,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 73.82177341477453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:deepseek-deepseek-v4-1-flash:f710e5b6860059c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1892.434782069571,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.7338376601718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 85,
      "max_score": null,
      "measured_at": "2026-09-25T15:11:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1848.2714359945248,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.44710951598115,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 249
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:deepseek-deepseek-v4-pro-0813:980c9c0ee71edcf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1828.4690903656574,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.9800600901681,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 360,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T01:36:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 360,
      "rating_method": "sequential_elo",
      "raw_elo": 1820.6789072396662,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.76004691232554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 267
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5:7c54c0ad2f51c786",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T04:44:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1825.7911435000174,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.49263343872869,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-5:5e4063ca612ddcd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1778.3379873195004,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 66.56758096324789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-8-flash:7ef3571107626567",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 97,
      "max_score": null,
      "measured_at": "2026-09-25T05:01:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1729.7591306402276,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.744543854931486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 145
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:qwen-qwen3-8-2-4t-a95b:80d9bb5405a8b814",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-09-25T14:11:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1721.8939183081075,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.23579274922259,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:tencent-hy3-preview:687d01bcbe0031c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 73,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T14:04:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1703.8573282748,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.8142594407856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-5-flash:27c90777b8ed242d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 131,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 141,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1684.2097414809214,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.06832955325717,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 171
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:z-ai-glm-5-3-flashx:bccbefa7a7bbd2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1669.4459210255652,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.763634521125965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 788,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 341,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 345,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 788,
      "rating_method": "sequential_elo",
      "raw_elo": 1646.2595980746028,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.54346412601527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 443
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:qwen-qwen3-8-27b:a0a78367379103f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T05:41:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 328,
      "rating_method": "sequential_elo",
      "raw_elo": 1634.441721343999,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.969406483876845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 196
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:tencent-hy4-preview:aa03f826bc323244",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T14:16:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1626.6083808764358,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.22864455350476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 136
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:mistralai-mistral-medium-3-5:eaf038eae77e915a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 110,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1621.6007828704835,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.99034820792066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 150
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:openai-gpt-oss-120b:e79c900fda7b779f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1587.9165865736045,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.825621514346786,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 324,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:bytedance-seed-seed-2-0-code:87a10b251e401fd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 163,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.3429566189945,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.55419811458228,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:z-ai-glm-5-2:d977e6638f849d00",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 132,
      "max_score": null,
      "measured_at": "2026-09-25T06:08:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.0018170020317,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.502993109011314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 338,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 160,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 338,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.4806021783322,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.21419120539835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 178
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 436,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 144,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 191,
      "max_score": null,
      "measured_at": "2026-09-23T13:14:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 436,
      "rating_method": "sequential_elo",
      "raw_elo": 1555.550717864032,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.18526830022632,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 245
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-fable-5:f2454da3451cc4f4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 137,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.2188092504707,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.95569071867738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 216,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-opus-4-8:10055d865d9a798b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 81,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 216,
      "rating_method": "sequential_elo",
      "raw_elo": 1551.5204169498527,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.42649291219306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1595,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 511,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 744,
      "max_score": null,
      "measured_at": "2026-09-25T15:42:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 1595,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.2139081889095,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.03780039623947,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 851
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-6-luna:6dc463949221612e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T05:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.7608692446993,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.82887430033942,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-6-terra:7c2a658c6918f6e6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 136,
      "max_score": null,
      "measured_at": "2026-09-25T05:25:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.726477915025,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 49.40159472806108,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 182
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 652,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 217,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 231,
      "max_score": null,
      "measured_at": "2026-09-25T06:00:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 474,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.3386272901982,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 46.23126106901278,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 243
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:deepseek-deepseek-v4-pro:91e0c8a35047bbc6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 164,
      "max_score": null,
      "measured_at": "2026-09-25T03:31:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.8810886057918,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.91113335979322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 314,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:meta-muse-glimmer-30b:b931921706d77dd0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 177,
      "max_score": null,
      "measured_at": "2026-09-25T03:52:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 314,
      "rating_method": "sequential_elo",
      "raw_elo": 1434.8861380916906,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.37253694835636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 133,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 179,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.1819943597798,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.507797739694716,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 196,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:stepfun-step-3-7-flash:4b833cb2e8aaef2e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T13:52:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 196,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.236482821177,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.50033505424671,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 281,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 156,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 281,
      "rating_method": "sequential_elo",
      "raw_elo": 1352.9565811557159,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.13255458513899,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 125
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 372,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:abf00b9c47e30ff5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 160,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 217,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 372,
      "rating_method": "sequential_elo",
      "raw_elo": 1306.8643133669477,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.88732222284614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 155
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 750,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 237,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 568,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 750,
      "rating_method": "sequential_elo",
      "raw_elo": 1109.881419184016,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.026580421066036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 182
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 754,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 229,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 599,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 754,
      "rating_method": "sequential_elo",
      "raw_elo": 1092.2996731742678,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.922871015070534,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 155
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-1-flash-lite:3af992128398834e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 155,
      "max_score": null,
      "measured_at": "2026-09-25T05:28:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 958.6120200971899,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 14.9868688465287,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-fable-5-1:76144460966d4171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-09-25T03:43:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 2318.897092303519,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 229
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:z-ai-glm-5-3:e8ce4aed95c7494d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 2165.3489889633206,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 90.7636514969772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 219
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-opus-5-5:493e35cd5b85e9e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-09-25T12:27:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 2102.4016317134924,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.98139509310396,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 762,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 261,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 128,
      "max_score": null,
      "measured_at": "2026-09-25T15:24:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 762,
      "rating_method": "sequential_elo",
      "raw_elo": 2054.014996548248,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 84.32762532825016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 605
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-fable-5:f2454da3451cc4f4",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-09-25T13:29:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 2056.7934715850724,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 84.1691849172907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 193
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-6-astra:5ccf2057056e4d7d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T06:05:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 2044.7653544019536,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 83.44269781880206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-8-flash:7ef3571107626567",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 2039.456503193102,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 83.10880420461697,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 178
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-6-sol:1b97e3eb94454fd6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 2034.2953622376588,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.84045926750574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:qwen-qwen3-8-2-4t-a95b:80d9bb5405a8b814",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-09-25T16:16:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 2014.87542955774,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.68122776333043,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 183
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 327,
      "rating_method": "sequential_elo",
      "raw_elo": 2003.9172974884755,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.2042772769244,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 236
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 328,
      "rating_method": "sequential_elo",
      "raw_elo": 1997.7574443097017,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 80.83425675693161,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 266
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:deepseek-deepseek-v4-flash:bd0b950926bd00a0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-09-25T03:13:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1985.940688516747,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 79.88316261692358,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-5:5e4063ca612ddcd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 72,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1968.2185266674333,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 78.62474263949787,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 162
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 180,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-opus-4-8:10055d865d9a798b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T14:10:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1960.5769388316662,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 78.12478117978807,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 151
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:tencent-hy4-preview:aa03f826bc323244",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-09-25T00:49:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1951.562346562994,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.83883887689821,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 175
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:meta-muse-spark-1-3:a15c2acfd980b456",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1938.01034564622,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.02031061725003,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 186
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-6-terra:7c2a658c6918f6e6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1936.8206165711558,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.93585154551911,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 173
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-6-luna:6dc463949221612e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1946.831431122891,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.68636345470857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:deepseek-deepseek-v4-pro:91e0c8a35047bbc6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1908.5199707434276,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.28091626993594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:deepseek-deepseek-v4-1-flash:f710e5b6860059c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-09-25T07:31:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1923.7890812127462,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 75.19336305189155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 330,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 330,
      "rating_method": "sequential_elo",
      "raw_elo": 1900.1607633818742,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.94353809455754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 250
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:qwen-qwen3-8-max-0902:b1160daf60583f67",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1885.8535702985014,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.87471300160755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:z-ai-glm-5-3-flashx:bccbefa7a7bbd2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1864.6192415868886,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.74427757233467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 194,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5:7c54c0ad2f51c786",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-09-25T13:21:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 194,
      "rating_method": "sequential_elo",
      "raw_elo": 1838.5649567775201,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.82103497731079,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-5-flash:27c90777b8ed242d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 100,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1817.5502813354785,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.73203415149305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 159
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 870,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 343,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 276,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 870,
      "rating_method": "sequential_elo",
      "raw_elo": 1772.4484196222327,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.13193639618068,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 501
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:x-ai-grok-4-6:5c921eacd53762a9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 105,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-09-25T06:11:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1706.161778721584,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.03521018257703,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:deepseek-deepseek-v4-pro-0813:980c9c0ee71edcf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 132,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 106,
      "max_score": null,
      "measured_at": "2026-09-25T13:25:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.2933466880772,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.08933985378316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 194
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 684,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 220,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 196,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 480,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.2310136332721,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.899996001122055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 249
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 339,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 152,
      "max_score": null,
      "measured_at": "2026-09-25T12:47:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 339,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.1089106507507,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 54.72441106072859,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 158
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 494,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 147,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 226,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 494,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.1150032151852,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.98273918474334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 253
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 166,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.2308172983269,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.611716687770866,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 179
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 486,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 149,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 225,
      "max_score": null,
      "measured_at": "2026-09-25T05:41:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 486,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.8009322240273,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.814135198615915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 238
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:xiaomi-mimo-v2-5:d38137ce389958c3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 119,
      "max_score": null,
      "measured_at": "2026-09-25T12:16:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.5775244954111,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 48.979799568566214,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 10.134219983223996,
      "unilateral_faults": null,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:z-ai-glm-5-2:d977e6638f849d00",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 117,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.476853557659,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.628065333452454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 820,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 253,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 429,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 820,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.2480292126502,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.48522862689852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 356
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1767,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 534,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 932,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 1767,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.7523429759424,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 45.38071106501111,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 801
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 207,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:abf00b9c47e30ff5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 116,
      "max_score": null,
      "measured_at": "2026-09-25T15:08:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 207,
      "rating_method": "sequential_elo",
      "raw_elo": 1290.8680313592329,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.7955878292642,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 328,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 215,
      "max_score": null,
      "measured_at": "2026-09-25T13:25:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 328,
      "rating_method": "sequential_elo",
      "raw_elo": 1265.2546120590778,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.59176650389889,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:stepfun-step-3-7-flash:4b833cb2e8aaef2e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 163,
      "max_score": null,
      "measured_at": "2026-09-23T20:21:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1221.4331847566114,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.73971611252159,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:qwen-qwen3-8-27b:a0a78367379103f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 155,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1220.0562223930833,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.70967503312307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:mistralai-mistral-medium-3-5:eaf038eae77e915a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 101,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 157,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1176.5381220136703,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 31.009077920581134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:tencent-hy3-preview:687d01bcbe0031c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 157,
      "max_score": null,
      "measured_at": "2026-09-25T14:14:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1131.9050992310254,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.190333048264026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:openai-gpt-oss-120b:e79c900fda7b779f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 180,
      "max_score": null,
      "measured_at": "2026-09-25T14:24:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1095.9008746850254,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.151419561181175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:bytedance-seed-seed-2-0-code:87a10b251e401fd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 96,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 181,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1079.957238668903,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.175682332360164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 213,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-1-flash-lite:3af992128398834e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 161,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 213,
      "rating_method": "sequential_elo",
      "raw_elo": 1071.5827214437497,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.574609551117437,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:inception-mercury-2-5-preview:e936b6bbd630c36b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 98,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 195,
      "max_score": null,
      "measured_at": "2026-09-25T14:21:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1046.529413953533,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.163090376598188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:z-ai-glm-5-3-flash:cea57e181d1e302f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 103,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 181,
      "max_score": null,
      "measured_at": "2026-09-25T05:13:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1008.7351772149632,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.860857984814505,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 254,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-6-astra:5ccf2057056e4d7d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-09-25T13:17:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 2285.455463434802,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 99.65604153579027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 250
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:z-ai-glm-5-3:e8ce4aed95c7494d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 2254.304779047959,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 97.58127501121015,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 247
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 506,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-fable-5-1:76144460966d4171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 211,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 506,
      "rating_method": "sequential_elo",
      "raw_elo": 2181.6000531046766,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 92.69213372868536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 476
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 2126.6926815025818,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 89.24673663502878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 312
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 77,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T13:11:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 2127.7356846387693,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 88.9097764968694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-opus-5-5:493e35cd5b85e9e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 2126.288409526174,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 88.05090981009354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-5:5e4063ca612ddcd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 82,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 234,
      "rating_method": "sequential_elo",
      "raw_elo": 2077.3800463802863,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 85.64043148326957,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 211
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-6-sol:1b97e3eb94454fd6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 2043.581158442173,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 82.55615873333252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1980.0748987537597,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 79.42432262453787,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 282
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:qwen-qwen3-8-27b:a0a78367379103f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 123,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-09-25T03:15:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1913.6688351436223,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 74.90167026913919,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 233
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:deepseek-deepseek-v4-pro:91e0c8a35047bbc6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 82,
      "max_score": null,
      "measured_at": "2026-09-25T04:30:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1875.5836068988096,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 72.21134396175917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 180
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:deepseek-deepseek-v4-pro-0813:980c9c0ee71edcf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T16:20:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1870.6286447706118,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 71.8729308953561,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:x-ai-grok-4-6:5c921eacd53762a9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T14:25:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1853.977814531143,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.75695908292762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:z-ai-glm-5-3-flashx:bccbefa7a7bbd2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T13:57:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1839.206746931014,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.6758710523356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1820.5862524640922,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.53774121733082,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 197
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-opus-4-8:10055d865d9a798b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 78,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-09-25T05:16:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1818.9857739328693,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 68.3072563481697,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 173
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:z-ai-glm-5-3-flash:cea57e181d1e302f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T04:36:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1777.3553951311483,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.67599407739836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 185
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:tencent-hy4-preview:aa03f826bc323244",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 118,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 115,
      "max_score": null,
      "measured_at": "2026-09-24T19:16:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1770.265865183308,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.23965370756527,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 177
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 118,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T13:05:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1756.5529772065865,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 64.43923630535639,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 233
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:deepseek-deepseek-v4-1-flash:f710e5b6860059c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T13:33:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1754.6299005256376,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 62.97794411108242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-8-flash:7ef3571107626567",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 117,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1714.4722670576302,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.419590951500844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-fable-5:f2454da3451cc4f4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 1712.247750873124,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 61.26424951289066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:x-ai-grok-4-7:bcff48978031cd50",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T14:05:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1719.264076773523,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 60.720023895279155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 896,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 369,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 348,
      "max_score": null,
      "measured_at": "2026-09-25T14:28:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 896,
      "rating_method": "sequential_elo",
      "raw_elo": 1685.8886855839849,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.59542381477149,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 548
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:qwen-qwen3-8-2-4t-a95b:80d9bb5405a8b814",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 106,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1682.1774714179971,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 59.229693911875664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 147
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 133,
      "max_score": null,
      "measured_at": "2026-09-25T13:23:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.705689755907,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 58.01956202861504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 211
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 236,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5:7c54c0ad2f51c786",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 236,
      "rating_method": "sequential_elo",
      "raw_elo": 1659.3017330955558,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 57.62738467323732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 143
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 462,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 141,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 197,
      "max_score": null,
      "measured_at": "2026-09-25T13:16:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 462,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.1437056065654,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 55.029289758171764,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 265
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:meta-muse-spark-1-3:a15c2acfd980b456",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 136,
      "max_score": null,
      "measured_at": "2026-09-25T14:20:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.257134738404,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 53.837866826293656,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:bytedance-seed-seed-2-0-code:87a10b251e401fd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 145,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 182,
      "max_score": null,
      "measured_at": "2026-09-25T12:32:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1583.1810602596506,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.83609631342515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 168
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 478,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 151,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 201,
      "max_score": null,
      "measured_at": "2026-09-25T12:58:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 478,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.2577772164589,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.304688764068835,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 277
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 490,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 151,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 243,
      "max_score": null,
      "measured_at": "2026-09-25T15:41:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 490,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.47687099777,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.849290405989954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 247
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 350,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-5-flash:27c90777b8ed242d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 143,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 175,
      "max_score": null,
      "measured_at": "2026-09-25T06:00:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 350,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.3071353060327,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.14767678741904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 175
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 712,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 233,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 245,
      "max_score": null,
      "measured_at": "2026-09-25T05:41:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 498,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.7674379150828,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 43.723138765545265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 253
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:meta-muse-glimmer-30b:b931921706d77dd0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 126,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 151,
      "max_score": null,
      "measured_at": "2026-09-25T14:10:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.0098804966221,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.90233392575276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 167
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 905,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 282,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 474,
      "max_score": null,
      "measured_at": "2026-09-25T16:02:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 905,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.5367015067034,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.77503608244635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 431
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 1868,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 572,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1017,
      "max_score": null,
      "measured_at": "2026-09-25T13:51:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 1868,
      "rating_method": "sequential_elo",
      "raw_elo": 1423.3727009046795,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 42.31127094485157,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 851
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-6-terra:7c2a658c6918f6e6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 145,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 213,
      "max_score": null,
      "measured_at": "2026-09-25T13:04:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1401.7920865935212,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.710585867697205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 338,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:deepseek-deepseek-v4-flash:bd0b950926bd00a0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 137,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 205,
      "max_score": null,
      "measured_at": "2026-09-25T14:59:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 338,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.4683915813177,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.43117903521025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 398,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 122,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 265,
      "max_score": null,
      "measured_at": "2026-09-25T14:31:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 398,
      "rating_method": "sequential_elo",
      "raw_elo": 1326.6538472650284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.73196065042729,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-6-luna:6dc463949221612e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-09-25T13:56:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1340.176559634495,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.2583774058522,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:openai-gpt-oss-120b:e79c900fda7b779f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 107,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 148,
      "max_score": null,
      "measured_at": "2026-09-25T05:19:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 252,
      "rating_method": "sequential_elo",
      "raw_elo": 1322.1159437249746,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.08448523875982,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:tencent-hy3-preview:687d01bcbe0031c5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 92,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 161,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.3955730790376,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.740095434691877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 244,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-1-flash-lite:3af992128398834e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 91,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 167,
      "max_score": null,
      "measured_at": "2026-09-25T04:07:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 244,
      "rating_method": "sequential_elo",
      "raw_elo": 1244.08501176749,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 29.827400148127907,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 241,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:stepfun-step-3-7-flash:4b833cb2e8aaef2e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 84,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 159,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 241,
      "rating_method": "sequential_elo",
      "raw_elo": 1175.991779846738,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.25307257035454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 272,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 213,
      "max_score": null,
      "measured_at": "2026-09-25T12:10:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 272,
      "rating_method": "sequential_elo",
      "raw_elo": 1099.4800470371417,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.225896354434745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:mistralai-mistral-medium-3-5:eaf038eae77e915a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 248,
      "max_score": null,
      "measured_at": "2026-09-25T14:26:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1035.7067945105448,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 16.002668622208688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:inception-mercury-2-5-preview:e936b6bbd630c36b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 248,
      "max_score": null,
      "measured_at": "2026-09-25T05:32:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1021.1793636804248,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 15.029011268175418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 262,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:z-ai-glm-5-2:d977e6638f849d00",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 236,
      "max_score": null,
      "measured_at": "2026-09-25T12:44:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 262,
      "rating_method": "sequential_elo",
      "raw_elo": 913.1207086604495,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 7.705163219117038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-fable-5-1:76144460966d4171",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 111,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5-1",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-09-25T13:59:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5.1",
      "model_slug": "claude-fable-5-1",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 2316.7113153732325,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5-1",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 254
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:qwen-qwen3-8-2-4t-a95b:80d9bb5405a8b814",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 112,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-09-25T05:18:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 2.4t A95B",
      "model_slug": "qwen-qwen3-8-2-4t-a95b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 2077.0836541057433,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-2.4t-a95b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 81.83360524090116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 239
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-6-astra:5ccf2057056e4d7d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 114,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-astra",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Astra",
      "model_slug": "gpt-6-astra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 2052.9844485033664,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-astra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 80.00375714481252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 230
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 408,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 135,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 408,
      "rating_method": "sequential_elo",
      "raw_elo": 2044.5328342692478,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 79.71896425856343,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 358
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-opus-5-5:493e35cd5b85e9e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-09-25T05:11:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5.5",
      "model_slug": "claude-opus-5-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 2033.2245619528665,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 77.55423891820166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 105
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:z-ai-glm-5-3:e8ce4aed95c7494d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T06:11:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3",
      "model_slug": "z-ai-glm-5-3",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 2009.920716462801,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 76.7126928285054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 218
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-opus-4-8:10055d865d9a798b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 86,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T06:53:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1928.5600377863639,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 70.45037043094591,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 183
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 468,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 169,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-09-25T15:24:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 468,
      "rating_method": "sequential_elo",
      "raw_elo": 1921.245931887621,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 69.8783085249793,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 380
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-6-sol:1b97e3eb94454fd6",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-sol",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-09-25T04:58:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Sol",
      "model_slug": "gpt-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1896.5477113421146,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 67.07517430996639,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:x-ai-grok-4-7:bcff48978031cd50",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.7",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-09-25T04:58:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.7",
      "model_slug": "x-ai-grok-4-7",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1875.9257072480004,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.7",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 65.39633278537028,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 340,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-09-25T13:54:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 340,
      "rating_method": "sequential_elo",
      "raw_elo": 1847.9538628823607,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 64.64982345476963,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 259
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 354,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 124,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-09-25T07:48:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 354,
      "rating_method": "sequential_elo",
      "raw_elo": 1832.936624227382,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.542324924259354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 274
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:meta-muse-spark-1-3:a15c2acfd980b456",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.3",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-09-25T05:50:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.3",
      "model_slug": "meta-muse-spark-1-3",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1834.236180208509,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 63.37299941780524,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 201
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 836,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 126,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 351,
      "draws": 126,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 255,
      "max_score": null,
      "measured_at": "2026-09-25T15:25:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 836,
      "rating_method": "sequential_elo",
      "raw_elo": 1749.339929690285,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 56.986504745106686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 455
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-6-luna:6dc463949221612e",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-6-luna",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-09-25T12:23:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-6 Luna",
      "model_slug": "gpt-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1710.4022553306731,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 52.85765337163106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 366,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 130,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 127,
      "max_score": null,
      "measured_at": "2026-09-25T15:53:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1679.5781289256847,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 51.92441638102823,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 197
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-5:5e4063ca612ddcd4",
      "capped_draws": 69,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 95,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-09-25T05:25:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1666.72185236652,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 50.64642374588417,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 160
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 300,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-5-flash:27c90777b8ed242d",
      "capped_draws": 101,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 85,
      "max_score": null,
      "measured_at": "2026-09-25T12:33:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 300,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.4769087588008,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 47.423524530455495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 114
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:bytedance-seed-seed-2-0-code:87a10b251e401fd3",
      "capped_draws": 153,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 133,
      "draws": 153,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-09-25T13:20:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Seed 2.0 Code",
      "model_slug": "bytedance-seed-seed-2-0-code",
      "plugin_success_rate": null,
      "provider": "ByteDance",
      "provider_key": "bytedance-seed",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1541.2520417101243,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "bytedance-seed",
        "provider_model": "bytedance-seed/seed-2.0-code",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 41.29002178163735,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:deepseek-deepseek-v4-1-flash:f710e5b6860059c6",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-09-25T15:24:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4.1 Flash",
      "model_slug": "deepseek-deepseek-v4-1-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.5999654523055,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4.1-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 40.80742778722643,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:qwen-qwen3-8-max-0902:b1160daf60583f67",
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max-0902",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-09-25T15:33:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max 0902",
      "model_slug": "qwen-qwen3-8-max-0902",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.9079956486037,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Xhigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max-0902",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Xhigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Xhigh",
        "reasoning_catalog_sha256": "010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 38.27023916972515,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 818,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 321,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 265,
      "draws": 321,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 237,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 818,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.2980039687752,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 37.63782150579934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 260
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-8-flash:7ef3571107626567",
      "capped_draws": 142,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 128,
      "draws": 142,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.8-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-09-25T12:52:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.8 Flash",
      "model_slug": "google-gemini-3-8-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.3669038906078,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.8-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 36.876211642013004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 1258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 577,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 404,
      "draws": 577,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 368,
      "max_score": null,
      "measured_at": "2026-09-25T13:01:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 1258,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.5589447123277,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.77303881930137,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 313
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-fable-5:f2454da3451cc4f4",
      "capped_draws": 118,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 116,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-09-25T13:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.357739447561,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 35.23351331310822,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 260,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:tencent-hy3-preview:687d01bcbe0031c5",
      "capped_draws": 80,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 91,
      "max_score": null,
      "measured_at": "2026-09-25T16:15:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 260,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.0276962334312,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 33.2889646152446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 338,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:qwen-qwen3-8-27b:a0a78367379103f7",
      "capped_draws": 118,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 140,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-27b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-09-25T02:59:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 27B",
      "model_slug": "qwen-qwen3-8-27b",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 338,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.3495104160008,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-27b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.556710798345804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 294,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:x-ai-grok-4-6:5c921eacd53762a9",
      "capped_draws": 124,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 128,
      "draws": 124,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.6",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 100,
      "max_score": null,
      "measured_at": "2026-09-25T13:14:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.6",
      "model_slug": "x-ai-grok-4-6",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 294,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.473702042447,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.6",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 32.37146553254912,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 207,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 144,
      "draws": 207,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-09-25T13:02:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1394.4072104012434,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 30.275745114985668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 718,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 254,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 233,
      "draws": 254,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 195,
      "max_score": null,
      "measured_at": "2026-09-25T13:41:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 498,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.7530278417635,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.321503645411784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 332,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-6-terra:7c2a658c6918f6e6",
      "capped_draws": 113,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 113,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 143,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 332,
      "rating_method": "sequential_elo",
      "raw_elo": 1366.4041855520484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 28.06620879280346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:stepfun-step-3-7-flash:4b833cb2e8aaef2e",
      "capped_draws": 197,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 88,
      "draws": 197,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-09-25T14:08:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.5866683300496,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 27.69802767311302,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:deepseek-deepseek-v4-pro:91e0c8a35047bbc6",
      "capped_draws": 202,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 113,
      "draws": 202,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-09-25T12:23:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1351.119642213177,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 26.795680762739188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:xiaomi-mimo-v2-5:d38137ce389958c3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 29,
      "draws": 180,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-09-25T13:08:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1354.476054487212,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 25.699884578572615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 10.672227745205968,
      "unilateral_faults": null,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 344,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:tencent-hy4-preview:aa03f826bc323244",
      "capped_draws": 214,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 214,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy4-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 115,
      "max_score": null,
      "measured_at": "2026-09-25T14:13:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy4 Preview",
      "model_slug": "tencent-hy4-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 344,
      "rating_method": "sequential_elo",
      "raw_elo": 1321.0852609664673,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy4-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.654353233120247,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:deepseek-deepseek-v4-flash:bd0b950926bd00a0",
      "capped_draws": 181,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 115,
      "draws": 181,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-09-25T14:44:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1322.8531658008642,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.618335850851498,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:z-ai-glm-5-3-flashx:bccbefa7a7bbd2f2",
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flashx",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.3 FlashX",
      "model_slug": "z-ai-glm-5-3-flashx",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.4329200529928,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flashx",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.546741166561926,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:meta-muse-glimmer-30b:b931921706d77dd0",
      "capped_draws": 191,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 119,
      "draws": 191,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-glimmer-30b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-09-25T15:08:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Glimmer 30B",
      "model_slug": "meta-muse-glimmer-30b",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.9198277734108,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-glimmer-30b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.41122888408428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 264,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5:7c54c0ad2f51c786",
      "capped_draws": 145,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 102,
      "draws": 145,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-09-25T14:33:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 264,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.722949607299,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 24.396279962390953,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 408,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 268,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 138,
      "draws": 268,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-09-25T14:04:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 408,
      "rating_method": "sequential_elo",
      "raw_elo": 1299.8401973546747,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.17459402857645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 476,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:abf00b9c47e30ff5",
      "capped_draws": 306,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 177,
      "draws": 306,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 148,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 476,
      "rating_method": "sequential_elo",
      "raw_elo": 1304.842053061372,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.090756402914224,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 329,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 203,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 130,
      "draws": 203,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 115,
      "max_score": null,
      "measured_at": "2026-09-25T07:01:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 329,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.7855986250888,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 23.076253765208513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 330,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:mistralai-mistral-medium-3-5:eaf038eae77e915a",
      "capped_draws": 198,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 134,
      "draws": 198,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 116,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 330,
      "rating_method": "sequential_elo",
      "raw_elo": 1294.977609210738,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.63778170243964,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 257,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 121,
      "draws": 257,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-09-25T14:13:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1288.4683412899717,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 22.172996399426747,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 286,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:z-ai-glm-5-2:d977e6638f849d00",
      "capped_draws": 209,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 120,
      "draws": 209,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-09-25T14:12:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.207605245957,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.16510261667805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 256,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-1-flash-lite:3af992128398834e",
      "capped_draws": 157,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 99,
      "draws": 157,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-09-25T14:27:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.5376688345202,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 21.012483894295887,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 282,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:z-ai-glm-5-3-flash:cea57e181d1e302f",
      "capped_draws": 201,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 108,
      "draws": 201,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.3-flash",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-09-25T11:57:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM 5.3 Flash",
      "model_slug": "z-ai-glm-5-3-flash",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 282,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.5083937551233,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.3-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 20.64380726893646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 412,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 257,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 142,
      "draws": 257,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 151,
      "max_score": null,
      "measured_at": "2026-09-25T14:07:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 412,
      "rating_method": "sequential_elo",
      "raw_elo": 1254.6639903797159,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.75166353849725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 276,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:inception-mercury-2-5-preview:e936b6bbd630c36b",
      "capped_draws": 182,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 118,
      "draws": 182,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inception/mercury-2.5-preview",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-09-25T15:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mercury 2.5 Preview",
      "model_slug": "inception-mercury-2-5-preview",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 276,
      "rating_method": "sequential_elo",
      "raw_elo": 1256.9096105084075,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "inception/mercury-2.5-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.591805674533738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 284,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:openai-gpt-oss-120b:e79c900fda7b779f",
      "capped_draws": 192,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 110,
      "draws": 192,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-09-25T12:06:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1252.1798924471577,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 19.258473624041308,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:deepseek-deepseek-v4-pro-0813:980c9c0ee71edcf8",
      "capped_draws": 185,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 109,
      "draws": 185,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-09-25T07:31:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro 0813",
      "model_slug": "deepseek-deepseek-v4-pro-0813",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1239.8410226636497,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro-0813",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260925-719069527ef4",
      "row_kind": "game",
      "score": 18.340229382396092,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "reviewed_model_pooling_official_qualification_v15",
      "snapshot_id": "20260925_163935",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    }
  ],
  "schema_version": 11,
  "snapshot_id": "20260925_163935",
  "suite_line_id": "gamebench2",
  "suite_version": "2-known8-r3"
}